Deep Learning for Vision

Oral presentations

The goal of the oral presentations is to carry out a bibliographic study and present the result to the class. You will team in up to two in this work.

Below is a list of papers organized in categories and sub-categories, which can help in finding papers related to each other. Choose a number of papers (not less than two, preferably not more than five) that are related to each other in a clear way. For instance, one is influenced by another, their methods are similar in some respect, they are using the same idea in different ways, or they attack the same problem from different sides. Papers should be interesting and not too hard to follow.

The paper list and its categories and sub-categories are too long, "noisy" and not very updated during the last 1-2 years. There may be important papers missing, and the existing ones may not so relevant, or overlapping across categories. It is there only to help in initiating the study, and is by no means a constraint. You are free to start e.g. at arXiv.org CVPR list, CVF open access, NeurIPS, ICLR, or anywhere else. You are also expected to find papers through citations, see below.

Report your choice by Sunday, December 15, 2019 through piazza, so that the whole class is notified. In case of overlap with another team, you may be asked to change your selection.

Study the papers in depth. Find how they are connected. Pay attention to related work and, through citations, try to identify other papers that are more relevant, more interesting or more recent. Feel free at this point to change your list of papers by removing some you found in the list and adding others that you found through studying. But you should not change the subject of your study entirely.

The presentations are on Monday, January 20, 2020.

You will have 8 minutes each for your talk plus 4 minutes for questions from the class, that is 20 minutes per team in total. You are expected to ask questions at other students' presentations. You will be evaluated based on your choice of papers, the way you have connected them into a story, and how you present them. You should focus on the main ideas. Implementation details are irrelevant for instance. Your goal is to present something interesting to your fellow students, so they learn something from your talk.

Action recognition

Convolution

Non-local Neural Networks [abstract]

Convolutional Two-Stream Network Fusion for Video Action Recognition [abstract]

ConvNet Architecture Search for Spatiotemporal Feature Learning [abstract]

Learning Spatiotemporal Features with 3D Convolutional Networks [abstract]

Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification [abstract]

A Closer Look at Spatiotemporal Convolutions for Action Recognition [abstract]

Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video [abstract]

Pooling

Generalized Rank Pooling for Activity Recognition [abstract]

Actionvlad: Learning Spatio-Temporal Aggregation for Action Classification [abstract]

Deep Temporal Linear Encoding Networks [abstract]

Order-Aware Convolutional Pooling for Video Based Action Recognition [abstract]

Higher-Order Pooling of CNN Features via Kernel Linearization for Action Recognition [abstract]

Second-Order Temporal Pooling for Action Recognition [abstract]

Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition [abstract]

Recurrent neural networks

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description [abstract]

Chained Predictions Using Convolutional Neural Networks [abstract]

Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video [abstract]

Unsupervised Learning of Video Representations Using LSTMs [abstract]

Beyond Short Snippets: Deep Networks for Video Classification [abstract]

RNN Fisher Vectors for Action Recognition and Image Annotation [abstract]

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification [abstract]

Adversarial examples

Attacks

Deepfool: a Simple and Accurate Method to Fool Deep Neural Networks [abstract]

Boosting Adversarial Attacks with Momentum [abstract]

Attacking the Madry Defense Model with $L_1$-based Adversarial Examples [abstract]

Towards Evaluating the Robustness of Neural Networks [abstract]

Adversarial Diversity and Hard Positive Generation [abstract]

Intriguing Properties of Neural Networks [abstract]

Adversarial Transformation Networks: Learning to Generate Adversarial Examples [abstract]

The Limitations of Deep Learning in Adversarial Settings [abstract]

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks [abstract]

Provably Minimally-Distorted Adversarial Examples [abstract]

Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods [abstract]

Explaining and Harnessing Adversarial Examples [abstract]

Adversarial Examples that Fool both Human and Computer Vision [abstract]

Defenses

Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics [abstract]

Foveation-Based Mechanisms Alleviate Adversarial Examples [abstract]

Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks [abstract]

Countering Adversarial Images using Input Transformations [abstract]

Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification [abstract]

When Not to Classify: Anomaly Detection of Attacks (ADA) on DNN Classifiers at Test Time [abstract]

Deflecting Adversarial Attacks with Pixel Deflection [abstract]

Detecting Adversarial Samples Using Density Ratio Estimates [abstract]

Analyzing Stability of Convolutional Neural Networks in the Frequency Domain [abstract]

Divide, Denoise, and Defend against Adversarial Attacks [abstract]

Network sensitivity

NO Need to Worry About Adversarial Examples in Object Detection in [abstract]

Analysis of Classifiers' Robustness to Adversarial Perturbations [abstract]

The Space of Transferable Adversarial Examples [abstract]

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach [abstract]

Robustness of Classifiers: From Adversarial to Random Noise [abstract]

With Friends Like These, Who Needs Adversaries? [abstract]

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images [abstract]

Architecture

Cascade

Feedback Networks [abstract]

Progressive Reasoning by Module Composition [abstract]

How to Stop Off-the-Shelf Deep Neural Networks from Overthinking [abstract]

Progressive Neural Networks for Image Classification [abstract]

Dense

Evenly Cascaded Convolutional Networks [abstract]

Log-DenseNet: How to Sparsify a DenseNet [abstract]

SparseNet: A Sparse DenseNet for Image Classification [abstract]

Dual Path Networks [abstract]

Sparsely Connected Convolutional Networks [abstract]

Densely Connected Convolutional Networks [abstract]

A Multipath Network for Object Detection [abstract]

Crossnets : A New Approach to Complex Learning [abstract]

Residual

Deep Residual Learning for Image Recognition [abstract]

Inception-V4, Inception-Resnet and the Impact of Residual Connections on Learning [abstract]

The Loss Surface of Residual Networks: Ensembles and the Role of Batch Normalization [abstract]

Deep Pyramidal Residual Networks [abstract]

Deep Cross Residual Learning for Multitask Visual Recognition [abstract]

The Shallow End: Empowering Shallower Deep-Convolutional Networks Through Auxiliary Outputs [abstract]

Weighted Residuals for Very Deep Networks [abstract]

Residual Networks Are Exponential Ensembles of Relatively Shallow Networks [abstract]

Diracnets: Training Very Deep Neural Networks Without Skip-Connections [abstract]

Learning Strict Identity Mappings in Deep Residual Networks [abstract]

Wide Residual Networks [abstract]

Resnet in Resnet: Generalizing Residual Architectures [abstract]

Identity Mappings in Deep Residual Networks [abstract]

Residual Networks of Residual Networks: Multilevel Residual Networks [abstract]

Wider or Deeper: Revisiting the Resnet Model for Visual Recognition [abstract]

Reversible

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models [abstract]

The Reversible Residual Network: Backpropagation Without Storing Activations [abstract]

i-RevNet: Deep Invertible Networks [abstract]

Reversible Architectures for Arbitrarily Deep Residual Neural Networks [abstract]

Classification

Fine-grained

Part-Stacked CNN for Fine-Grained Visual Categorization [abstract]

Fine-Grained Pose Prediction, Normalization, and Recognition [abstract]

Mining Discriminative Triplets of Patches for Fine-Grained Classification [abstract]

Part Detector Discovery in Deep Convolutional Neural Networks [abstract]

Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach [abstract]

Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition [abstract]

Bilinear CNN Models for Fine-Grained Visual Recognition [abstract]

Deep Deformation Network for Object Landmark Localization [abstract]

Object-Centric Sampling for Fine-Grained Image Classification [abstract]

Loss functions

Impostor Networks for Fast Fine-Grained Recognition [abstract]

Decoupled Networks [abstract]

Dynamic-structured Semantic Propagation Network [abstract]

Rethinking Feature Distribution for Loss Functions in Image Classification [abstract]

Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation [abstract]

Be Careful What You Backpropagate: A Case for Linear Output Activations & Gradient Boosting [abstract]

Beyond One-Hot Encoding: Lower Dimensional Target Embedding [abstract]

Clustering

Variational Deep Embedding: A Generative Approach to Clustering [abstract]

Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images [abstract]

Semi-Supervised Learning for Convolutional Neural Networks via Online Graph Construction [abstract]

Neural Network-Based Clustering Using Pairwise Constraints [abstract]

A Deep Matrix Factorization Method for Learning Attribute Representations [abstract]

Clustering with Deep Learning: Taxonomy and New Methods [abstract]

Unsupervised Deep Embedding for Clustering Analysis [abstract]

Learning A Task-Specific Deep Architecture for Clustering [abstract]

Adversarial Autoencoders [abstract]

ClusterNet : Semi-Supervised Clustering using Neural Networks [abstract]

CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data [abstract]

Scalable Laplacian K-modes [abstract]

Learning to cluster in order to transfer across domains and tasks [abstract]

Deep Continuous Clustering [abstract]

Convolution

Adaptive

Autofocus Layer for Semantic Segmentation [abstract]

Irregular Convolutional Neural Networks [abstract]

Dynamic Filter Networks [abstract]

Dense Transformer Networks [abstract]

Deformable Part Networks [abstract]

Dynamic Steerable Blocks in Deep Residual Networks [abstract]

Local Binary Pattern Networks [abstract]

Spatially-Adaptive Filter Units for Deep Neural Networks [abstract]

Learning Filter Scale and Orientation In CNNs [abstract]

Dynamic Sampling Convolutional Neural Networks [abstract]

3D Morphable Models as Spatial Transformer Networks [abstract]

Spatial Transformer Networks [abstract]

Learning Dilation Factors for Semantic Segmentation of Street Scenes [abstract]

Deformable Convolutional Networks [abstract]

Active Convolution: Learning the Shape of Convolution for Image Classification [abstract]

Capsules

Fast Dynamic Routing Based on Weighted Kernel Density Estimation [abstract]

Sparse Unsupervised Capsules Generalize Better [abstract]

Dynamic Routing Between Capsules [abstract]

Capsule networks for low-data transfer learning [abstract]

Graph Capsule Convolutional Neural Networks [abstract]

Group Equivariant Capsule Networks [abstract]

CapsGAN: Using Dynamic Routing for Generative Adversarial Networks [abstract]

Neural Network Encapsulation [abstract]

Variational Capsules for Image Analysis and Synthesis [abstract]

Dilation

Dilated Residual Networks [abstract]

Rethinking Atrous Convolution for Semantic Image Segmentation [abstract]

Multi-Scale Context Aggregation By Dilated Convolutions [abstract]

Dense CNN Learning with Equivalent Mappings [abstract]

WaveNet: A Generative Model for Raw Audio [abstract]

Frequency

Fast Training of Convolutional Networks Through FFTs [abstract]

Fast Convolutional Nets with Fbfft: A GPU Performance Evaluation [abstract]

Fast Neural Networks with Circulant Projections [abstract]

Shapenet: Convolutional Neural Networks on Non-Euclidean Manifolds [abstract]

Graph

Diffusion-Convolutional Neural Networks [abstract]

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering [abstract]

Graph Based Convolutional Neural Network [abstract]

Deep Convolutional Networks on Graph-Structured Data [abstract]

Graph Capsule Convolutional Neural Networks [abstract]

Few-Shot Learning with Graph Neural Networks [abstract]

Dynamic Filters in Graph Convolutional Networks [abstract]

A Generalization of Convolutional Neural Networks to Graph-Structured Data [abstract]

Spectral Networks and Locally Connected Networks on Graphs [abstract]

Geometric Deep Learning: Going Beyond Euclidean Data [abstract]

Semi-Supervised Classification with Graph Convolutional Networks [abstract]

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs [abstract]

Graph/co-ordinates

Unifying Local and Non-Local Signal Processing with Graph CNNs [abstract]

SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels [abstract]

Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds [abstract]

Dynamic Graph CNN for Learning on Point Clouds [abstract]

PointConv: Deep Convolutional Networks on 3D Point Clouds [abstract]

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters [abstract]

Point-wise Convolutional Neural Network [abstract]

PointCNN [abstract]

Group

Deep Expander Networks: Efficient Deep Networks from Graph Theory [abstract]

Multi-Fiber Networks for Video Recognition [abstract]

Interleaved Group Convolutions for Deep Neural Networks [abstract]

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices [abstract]

Wide Compression: Tensor Ring Nets [abstract]

Deep Learning with Separable Convolutions [abstract]

Aggregated Residual Transformations for Deep Neural Networks [abstract]

IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks [abstract]

Non-Parametric Transformation Networks [abstract]

IGCV2: Interleaved Structured Sparse Convolutional Neural Networks [abstract]

clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions [abstract]

Non-local

Squeeze-and-Excitation Networks [abstract]

Neural Nearest Neighbors Networks [abstract]

$A^2$-Nets: Double Attention Networks [abstract]

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks [abstract]

Non-local Neural Networks [abstract]

Compact Generalized Non-local Network [abstract]

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks [abstract]

Quantized

Binaryconnect: Training Deep Neural Networks with Binary Weights During Propagations [abstract]

Training wide residual networks for deployment using a single bit for each weight [abstract]

Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights [abstract]

Compressing Deep Convolutional Networks Using Vector Quantization [abstract]

Local Binary Pattern Networks [abstract]

Deep Neural Networks Are Robust to Weight Binarization and Other Non-Linear Distortions [abstract]

Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding [abstract]

Energy Efficient Hadamard Neural Networks [abstract]

PACT: Parameterized Clipping Activation for Quantized Neural Networks [abstract]

Local Binary Convolutional Neural Networks [abstract]

XNOR-Net: Imagenet Classification Using Binary Convolutional Neural Networks [abstract]

Ternary Weight Networks [abstract]

Deep Local Binary Patterns [abstract]

Low-rank

Factorized Convolutional Neural Networks [abstract]

Rank-1 Convolutional Neural Network [abstract]

Network Decoupling: From Regular to Depthwise Separable Convolutions [abstract]

Speeding-Up Convolutional Neural Networks Using Fine-Tuned CP-Decomposition [abstract]

Coordinating Filters for Faster Deep Neural Networks [abstract]

Compression of Fully-Connected Layer in Neural Network By Kronecker Product [abstract]

Decomposeme: Simplifying Convnets for End-to-End Learning [abstract]

Exploiting Local Structures with the Kronecker Layer in Convolutional Networks [abstract]

Training CNNs with Low-Rank Filters for Efficient Image Classification [abstract]

Convolutional Neural Networks with Low-Rank Regularization [abstract]

Sparse

Generalizing the Convolution Operator to Extend CNNs to Irregular Domains [abstract]

Sparsity Invariant CNNs [abstract]

PerforatedCNNs: Acceleration Through Elimination of Redundant Convolutions [abstract]

Superpixel Convolutional Networks Using Bilateral Inceptions [abstract]

Training Sparse Neural Networks [abstract]

Submanifold Sparse Convolutional Networks [abstract]

Broadcasting Convolutional Network [abstract]

Point Convolutional Neural Networks by Extension Operators [abstract]

Why Regularized Auto-Encoders Learn Sparse Representation? [abstract]

Numerical Coordinate Regression with Convolutional Neural Networks [abstract]

Structured

Learning Steerable Filters for Rotation Equivariant CNNs [abstract]

Structured Receptive Fields in CNNs [abstract]

Perturbative Neural Networks [abstract]

Scaling the Scattering Transform: Deep Hybrid Networks [abstract]

RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks [abstract]

Gabor Convolutional Networks [abstract]

Structured Convolution Matrices for Energy-Efficient Deep Learning [abstract]

Detection

Architecture

Focal Loss for Dense Object Detection [abstract]

Feature Pyramid Networks for Object Detection [abstract]

Beyond Skip Connections: Top-Down Modulation for Object Detection [abstract]

DetNet: A Backbone network for Object Detection [abstract]

DSSD : Deconvolutional Single Shot Detector [abstract]

Attention

G-CNN: an Iterative Grid Based Object Detector [abstract]

Attentional Network for Visual Object Detection [abstract]

Spatial Memory for Context Reasoning in Object Detection [abstract]

Single-Shot Refinement Neural Network for Object Detection [abstract]

Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection [abstract]

Pronet: Learning to Propose Object-Specific Boxes for Cascaded Neural Networks [abstract]

Hierarchical Object Detection with Deep Reinforcement Learning [abstract]

Attend Refine Repeat: Active Box Proposal Generation via in-Out Localization [abstract]

Adaptive Object Detection Using Adjacency and Zoom Prediction [abstract]

Multiple Object Recognition with Visual Attention [abstract]

Learning to Decompose for Object Detection and Instance Segmentation [abstract]

Object proposals

ME R-CNN: Multi-Expert Region-Based CNN for Object Detection [abstract]

Arbitrary-Oriented Scene Text Detection via Rotation Proposals [abstract]

Deepproposals: Hunting Objects and Actions By Cascading Deep Convolutional Layers [abstract]

Boosting Convolutional Features for Robust Object Proposals [abstract]

Scale-Aware Pixel-Wise Object Proposal Networks [abstract]

Scalable Object Detection Using Deep Neural Networks [abstract]

Active Object Localization with Deep Reinforcement Learning [abstract]

Toward Scale-Invariance and Position-Sensitive Region Proposal Networks [abstract]

Learning to Segment Object Candidates [abstract]

DeepProposal: Hunting Objects By Cascading Deep Convolutional Layers [abstract]

Scalable, High-Quality Object Detection [abstract]

Deepbox: Learning Objectness with Convolutional Networks [abstract]

Object-Proposal Evaluation Protocol Is 'Gameable' [abstract]

Counting

C-WSL: Count-guided Weakly Supervised Localization [abstract]

An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting [abstract]

Crowd counting via scale-adaptive convolutional neural network [abstract]

Learning Short-Cut Connections for Object Counting [abstract]

Deepsetnet: Predicting Sets with Deep Neural Networks [abstract]

Learning to Point and Count [abstract]

Non-maximum suppression

A Convnet for Non-Maximum Suppression [abstract]

Relation Networks for Object Detection [abstract]

Improving Object Detection with One Line of Code [abstract]

Learning Detection with Diverse Proposals [abstract]

Learning Non-Maximum Suppression [abstract]

Parts-based

Part-Stacked CNN for Fine-Grained Visual Categorization [abstract]

Joint Object and Part Segmentation Using Deep Learned Potentials [abstract]

Deepm: A Deep Part-Based Model for Object Detection and Semantic Part Localization [abstract]

Do We Need More Training Data? [abstract]

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks [abstract]

Deepid-Net: Deformable Deep Convolutional Neural Networks for Object Detection [abstract]

Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition [abstract]

Deformable Part-based Fully Convolutional Network for Object Detection [abstract]

Deformable Part Models Are Convolutional Neural Networks [abstract]

Object Detection Networks on Convolutional Feature Maps [abstract]

Do Semantic Parts Emerge in Convolutional Neural Networks? [abstract]

Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net [abstract]

Window-Object Relationship Guided Representation Learning for Generic Object Detections [abstract]

Proposal-based

Feature Selective Networks for Object Detection [abstract]

CoupleNet: Coupling Global Structure with Local Parts for Object Detection [abstract]

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation [abstract]

MetaAnchor: Learning to Detect Objects with Customized Anchors [abstract]

Fast R-CNN [abstract]

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [abstract]

Training Region-Based Object Detectors with Online Hard Example Mining [abstract]

Hypernet: Towards Accurate Region Proposal Generation and Joint Object Detection [abstract]

R-FCN: Object Detection via Region-Based Fully Convolutional Networks [abstract]

PVANET: Deep But Lightweight Neural Networks for Real-Time Object Detection [abstract]

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks [abstract]

Single-shot

Single-Shot Object Detection with Enriched Semantics [abstract]

Generic Object Detection with Dense Neural Patterns and Regionlets [abstract]

Single-Shot Refinement Neural Network for Object Detection [abstract]

FSSD: Feature Fusion Single Shot Multibox Detector [abstract]

YOLO9000: Better, Faster, Stronger [abstract]

SSD: Single Shot Multibox Detector [abstract]

Learning to Detect and Localize Many Objects From Few Examples [abstract]

Object detection at 200 Frames Per Second [abstract]

You Only Look Once: Unified, Real-Time Object Detection [abstract]

R-CNN Minus R [abstract]

Weakly-supervised

On learning to localize objects with minimal supervision [abstract]

Multiple Instance Detection Network with Online Instance Classifier Refinement [abstract]

From Image-Level to Pixel-Level Labeling with Convolutional Networks [abstract]

Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks [abstract]

Weakly Supervised Deep Detection Networks [abstract]

TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection [abstract]

Contextlocnet: Context-Aware Deep Network Models for Weakly Supervised Localization [abstract]

Edge detection

High-for-Low and Low-for-High: Efficient Boundary Detection From Deep Object Features and Its Applications to High-Level Vision [abstract]

Semantic Segmentation with Boundary Neural Fields [abstract]

Dynamic Steerable Blocks in Deep Residual Networks [abstract]

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network [abstract]

Deepedge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection [abstract]

Contour Detection Using Cost-Sensitive Convolutional Neural Networks [abstract]

Pushing the Boundaries of Boundary Detection Using Deep Learning [abstract]

Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction [abstract]

Holistically-Nested Edge Detection [abstract]

Shadow Optimization From Structured Deep Edge Detection [abstract]

Face

Recognition

Megaface: A Million Faces for Recognition at Scale [abstract]

Multi-View Face Detection Using Deep Convolutional Neural Networks [abstract]

Towards the Design of an End-to-End Automated System for Image and Video-Based Recognition [abstract]

Deeply Learned Face Representations Are Sparse, Selective, and Robust [abstract]

Face Identification with Bilinear CNNs [abstract]

Deep Learning Face Representation By Joint Identification-Verification [abstract]

Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues [abstract]

When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition [abstract]

Few-shot learning

Few Shot Learning with Simplex [abstract]

Dynamic Few-Shot Visual Learning without Forgetting [abstract]

Low-Shot Learning with Large-Scale Diffusion [abstract]

Few-Shot Image Recognition By Predicting Parameters From Activations [abstract]

Few-shot Learning by Exploiting Visual Concepts within CNNs [abstract]

Low-Shot Visual Object Recognition [abstract]

Prototypical Networks for Few-shot Learning [abstract]

Learning with Imprinted Weights [abstract]

TADAM: Task dependent adaptive metric for improved few-shot learning [abstract]

Incremental Few-Shot Learning with Attention Attractor Networks [abstract]

Improving Generalization via Scalable Neighborhood Component Analysis [abstract]

Invariance

Measuring

How Well Can a CNN Marginalize Simple Nuisances It Is Designed for? [abstract]

Manitest: Are Classifiers Really Invariant? [abstract]

Mirror, Mirror on the Wall, Tell Me, Is the Error Small? [abstract]

Geodesics of Learned Representations [abstract]

What Is Holding Back Convnets for Detection? [abstract]

Why do deep convolutional networks generalize so poorly to small image transformations? [abstract]

Studying Invariances of Trained Convolutional Neural Networks [abstract]

Confidence from Invariance to Image Transformations [abstract]

What Can We Learn About CNNs From a Large Scale Controlled Object Dataset? [abstract]

Generalization Error of Invariant Classifiers [abstract]

Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images [abstract]

Normalization

Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis [abstract]

Inverse Compositional Spatial Transformer Networks [abstract]

Deformable Classifiers [abstract]

Spatial Transformer Networks [abstract]

Rotation

Learning Steerable Filters for Rotation Equivariant CNNs [abstract]

CubeNet: Equivariance to 3D Rotation and Translation [abstract]

Deformable Classifiers [abstract]

Scaling the Scattering Transform: Deep Hybrid Networks [abstract]

Deep Rotation Equivariant Network [abstract]

TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks [abstract]

Rotation Equivariance and Invariance in Convolutional Neural Networks [abstract]

Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification [abstract]

Polar Transformer Networks [abstract]

Harmonic Networks: Deep Translation and Rotation Equivariance [abstract]

Rotation Equivariant Vector Field Networks [abstract]

Rotation-Invariant Convolutional Neural Networks for Galaxy Morphology Prediction [abstract]

Exploiting Cyclic Symmetry in Convolutional Neural Networks [abstract]

Steerable CNNs [abstract]

Gabor Convolutional Networks [abstract]

Scale

Autofocus Layer for Semantic Segmentation [abstract]

Looking Outside of the Box: Object Detection and Localization with Multi-Scale Patterns [abstract]

Fast Training of Convolutional Neural Networks via Kernel Rescaling [abstract]

Competitive Multi-Scale Convolution [abstract]

Autoscaler: Scale-Attention Networks for Visual Correspondence [abstract]

Neural Multigrid [abstract]

Wavelet Convolutional Neural Networks [abstract]

An Analysis of Scale Invariance in Object Detection : SNIP [abstract]

What Happened to My Dog in That Network: Unraveling Top-Down Generators in Convolutional Neural Networks [abstract]

Scale-Invariant Convolutional Neural Network [abstract]

Attention to Scale: Scale-Aware Semantic Image Segmentation [abstract]

Locally Scale-Invariant Convolutional Neural Networks [abstract]

Learning Across Scales : A Multiscale Method for Convolution Neural Networks [abstract]

Learning Scale-Variant and Scale-Invariant Features for Deep Image Classification [abstract]

Revisiting Dilated Convolution- A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation [abstract]

Learning

Domain adaptation

Incremental Learning Through Deep Adaptation [abstract]

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons [abstract]

Few-Shot Adversarial Domain Adaptation [abstract]

Revisiting Batch Normalization for Practical Domain Adaptation [abstract]

Unsupervised Domain Adaptation By Backpropagation [abstract]

Deep Domain Confusion: Maximizing for Domain Invariance [abstract]

Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights [abstract]

Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach [abstract]

CyCADA: Cycle-Consistent Adversarial Domain Adaptation [abstract]

Associative Domain Adaptation [abstract]

Lightweight Unsupervised Domain Adaptation By Convolutional Filter Reconstruction [abstract]

Deep Transfer Network: Unsupervised Domain Adaptation [abstract]

Optimal Transport for Deep Joint Transfer Learning [abstract]

Beyond Sharing Weights for Deep Domain Adaptation [abstract]

Deeper, Broader and Artier Domain Generalization [abstract]

Learning Deep Feature Representations with Domain Guided Dropout for Person Re-Identification [abstract]

Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network [abstract]

Learning to cluster in order to transfer across domains and tasks [abstract]

Generalizing to Unseen Domains via Adversarial Data Augmentation [abstract]

The Multiverse Loss for Robust Transfer Learning [abstract]

Incremental

End-to-End Incremental Learning [abstract]

Progressive Neural Networks [abstract]

The Extreme Value Machine [abstract]

DeeSIL: Deep-Shallow Incremental Learning [abstract]

Learning Without Forgetting [abstract]

Differentiable plasticity: training plastic neural networks with backpropagation [abstract]

Reinforced Continual Learning [abstract]

Incremental Learning Through Deep Adaptation [abstract]

Memory Aware Synapses: Learning what (not) to forget [abstract]

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning [abstract]

Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights [abstract]

Icarl: Incremental Classifier and Representation Learning [abstract]

Learning without Memorizing [abstract]

Incremental Few-Shot Learning with Attention Attractor Networks [abstract]

Selfless Sequential Learning [abstract]

Pathnet: Evolution Channels Gradient Descent in Super Neural Networks [abstract]

Normalization

Normalization of Neural Networks using Analytic Variance Propagation [abstract]

Projection Based Weight Normalization for Deep Neural Networks [abstract]

Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct? [abstract]

Group Normalization [abstract]

Shifting Mean Activation Towards Zero with Bipolar Activation Functions [abstract]

Understanding Regularization in Batch Normalization [abstract]

Differentiable Learning-to-Normalize via Switchable Normalization [abstract]

Batch Normalization: Accelerating Deep Network Training By Reducing Internal Covariate Shift [abstract]

Layer Normalization [abstract]

Regularization

Swapout: Learning an Ensemble of Deep Architectures [abstract]

Revisiting Batch Normalization for Practical Domain Adaptation [abstract]

In Search of the Real Inductive Bias: on the Role of Implicit Regularization in Deep Learning [abstract]

Fractional Max-Pooling [abstract]

Improved Regularization of Convolutional Neural Networks with Cutout [abstract]

Blockout: Dynamic Model Selection for Hierarchical Deep Networks [abstract]

Graphconnect: A Regularization Framework for Neural Networks [abstract]

Understanding Regularization in Batch Normalization [abstract]

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks [abstract]

Binaryconnect: Training Deep Neural Networks with Binary Weights During Propagations [abstract]

Memory Bounded Deep Convolutional Networks [abstract]

Batch Normalization: Accelerating Deep Network Training By Reducing Internal Covariate Shift [abstract]

Network ensembles

Snapshot Ensembles: Train 1, get M for free [abstract]

Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer [abstract]

Distilling the Knowledge in a Neural Network [abstract]

Collaborative Learning for Deep Neural Networks [abstract]

Why M Heads Are Better Than One: Training a Diverse Ensemble of Deep Networks [abstract]

SGDR: Stochastic Gradient Descent with Warm Restarts [abstract]

Local features

Domain-Size Pooling in Local Descriptors: DSP-SIFT [abstract]

PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors [abstract]

Fracking Deep Convolutional Image Descriptors [abstract]

Working Hard to Know Your Neighbor's Margins: Local Descriptor Learning Loss [abstract]

Learning to Assign Orientations to Feature Points [abstract]

Handcrafted Local Features Are Convolutional Neural Networks [abstract]

Unsupervised Feature Learning By Augmenting Single Images [abstract]

Shapenet: Convolutional Neural Networks on Non-Euclidean Manifolds [abstract]

Learning to Compare Image Patches via Convolutional Neural Networks [abstract]

Weakly Supervised Patchnets: Describing and Aggregating Local Patches for Scene Recognition [abstract]

Local Descriptors Optimized for Average Precision [abstract]

Detection

SuperPoint: Self-Supervised Interest Point Detection and Description [abstract]

Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection [abstract]

LIFT: Learned Invariant Feature Transform [abstract]

Learning Covariant Feature Detectors [abstract]

SIPS: Unsupervised Succinct Interest Points [abstract]

LF-Net: Learning Local Features from Images [abstract]

Multi-task learning

One Network to Solve Them All --: Solving Linear Inverse Problems Using Deep Projection Models [abstract]

Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning [abstract]

Ubernet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory [abstract]

Pixelnet: Towards a General Pixel-Level Architecture [abstract]

Deep Cross Residual Learning for Multitask Visual Recognition [abstract]

Pathnet: Evolution Channels Gradient Descent in Super Neural Networks [abstract]

Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction [abstract]

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks [abstract]

Three for one and one for three: Flow, Segmentation, and Surface Normals [abstract]

Pose estimation

Humans

Human Pose Estimation with Iterative Error Feedback [abstract]

Learning to Estimate 3D Human Pose and Shape from a Single Color Image [abstract]

Deep Deformation Network for Object Landmark Localization [abstract]

Convolutional Pose Machines [abstract]

Chained Predictions Using Convolutional Neural Networks [abstract]

Learning to Estimate Pose By Watching Videos [abstract]

Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video [abstract]

Ordinal Depth Supervision for 3D Human Pose Estimation [abstract]

Deepcut: Joint Subset Partition and Labeling for Multi Person Pose Estimation [abstract]

Towards Accurate Multi-Person Pose Estimation in the Wild [abstract]

Associative Embedding-End-to-End Learning for Joint Detection and Grouping [abstract]

Personalizing Human Video Pose Estimation [abstract]

Recurrent Human Pose Estimation [abstract]

P-CNN: Pose-Based CNN Features for Action Recognition [abstract]

Hands Deep in Deep Learning for Hand Pose Estimation [abstract]

Deeppose: Human Pose Estimation via Deep Neural Networks [abstract]

3D Human Pose Estimation = 2D Pose Estimation + Matching [abstract]

Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape From a Single Image [abstract]

Deep Convolutional Inverse Graphics Network [abstract]

Deepercut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model [abstract]

Numerical Coordinate Regression with Convolutional Neural Networks [abstract]

Objects

Convolutional Neural Networks for Joint Object Detection and Pose Estimation: A Comparative Study [abstract]

Rotationnet: Learning Object Classification Using Unsupervised Viewpoint Estimation [abstract]

DeepKey: Towards End-to-End Physical Key Replication From a Single Photograph [abstract]

Templatenet for Depth-Based Object Instance Recognition [abstract]

Learning Descriptors for Object Recognition and 3D Pose Estimation [abstract]

Multi-View Convolutional Neural Networks for 3D Shape Recognition [abstract]

DeepIM: Deep Iterative Matching for 6D Pose Estimation [abstract]

Inferring 3D Object Pose in RGB-D Images [abstract]

Deep Cuboid Detection: Beyond 2D Bounding Boxes [abstract]

3D Pose Estimation and 3D Model Retrieval for Objects in the Wild [abstract]

3D Object Class Detection in the Wild [abstract]

3D Bounding Box Estimation Using Deep Learning and Geometry [abstract]

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views [abstract]

Registration/correspondence

Universal Correspondence Network [abstract]

Matching-CNN Meets KNN: Quasi-Parametric Human Parsing [abstract]

Deep Convolutional Matching [abstract]

Learning to Align Images using Weak Geometric Supervision [abstract]

Dense

Unsupervised Feature Learning for Dense Correspondences Across Scenes [abstract]

Autoscaler: Scale-Attention Networks for Visual Correspondence [abstract]

DGC-Net: Dense Geometric Correspondence Network [abstract]

Deep Convolutional Matching [abstract]

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence Estimation [abstract]

Neighbourhood Consensus Networks [abstract]

Fully-Trainable Deep Matching [abstract]

Parts-based

End-to-end weakly-supervised semantic alignment [abstract]

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence [abstract]

Neural Best-Buddies: Sparse Cross-Domain Correspondence [abstract]

Universal Correspondence Network [abstract]

Scnet: Learning Semantic Correspondence [abstract]

Anchornet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching [abstract]

Retrieval

Fine-tuning

End-to-End Learning of Deep Visual Representations for Image Retrieval [abstract]

Fine-Tuning CNN Image Retrieval with No Human Annotation [abstract]

Deep Image Retrieval: Learning Global Representations for Image Search [abstract]

Learning Non-Metric Visual Similarity for Image Retrieval [abstract]

CNN Image Retrieval Learns From Bow: Unsupervised Fine-Tuning with Hard Examples [abstract]

Pooling

Weakly Supervised Soft-detection-based Aggregation Method for Image Retrieval [abstract]

Context Aware Query Image Representation for Particular Object Retrieval [abstract]

Object Level Deep Feature Pooling for Compact Image Representation [abstract]

Aggregating Deep Convolutional Features for Image Retrieval [abstract]

Particular Object Retrieval with Integral Max-Pooling of CNN Activations [abstract]

Embedding Based on Function Approximation for Large Scale Image Search [abstract]

Deep Feature Aggregation with Heat Diffusion for Image Retrieval [abstract]

Netvlad: CNN Architecture for Weakly Supervised Place Recognition [abstract]

From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval [abstract]

Deep Convolutional Features for Image Based Retrieval and Scene Categorization [abstract]

Faster R-CNN Features for Instance Search [abstract]

Re-ranking

Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval [abstract]

Mining on Manifolds: Metric Learning without Labels [abstract]

Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking [abstract]

Fast Spectral Ranking for Similarity Search [abstract]

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations [abstract]

Person re-identification

Let Features Decide for Themselves: Feature Mask Network for Person Re-identification [abstract]

Adaptive Re-ranking of Deep Feature for Person Re-identification [abstract]

Adversarial Open-World Person Re-Identification [abstract]

Re-ID done right: towards good practices for person re-identification [abstract]

In Defense of the Classification Loss for Person Re-Identification [abstract]

The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching [abstract]

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification [abstract]

Saliency

Unsupervised deep object discovery for instance recognition [abstract]

Class-Weighted Convolutional Features for Visual Instance Search [abstract]

Saliency Weighted Convolutional Features for Instance Search [abstract]

Cross-Dimensional Weighting for Aggregated Deep Convolutional Features [abstract]

Image Retrieval with Deep Local Features and Attention-Based Keypoints [abstract]

Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps [abstract]

Attention-aware Generalized Mean Pooling for Image Retrieval [abstract]

Spatial

CNN Features Off-the-Shelf: an Astounding Baseline for Recognition [abstract]

Deep Region Hashing for Efficient Large-Scale Instance Search From Images [abstract]

Particular Object Retrieval with Integral Max-Pooling of CNN Activations [abstract]

Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval with VLAD and Deep-Learning-Based Descriptors [abstract]

Image Retrieval with Deep Local Features and Attention-Based Keypoints [abstract]

Visual Instance Retrieval with Deep Convolutional Networks [abstract]

Saliency

Pixel Objectness [abstract]

Training Deep Networks to be Spatially Sensitive [abstract]

Deepsaliency: Multi-Task Deep Neural Network Model for Salient Object Detection [abstract]

Visual Saliency Based on Multiscale Deep Features [abstract]

Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on Imagenet [abstract]

Deepfix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations [abstract]

Three Birds One Stone: A Unified Framework for Salient Object Segmentation, Edge Detection and Skeleton Extraction [abstract]

Salient Object Subitizing [abstract]

Salgan: Visual Saliency Prediction with Generative Adversarial Networks [abstract]

Reverse Attention for Salient Object Detection [abstract]

Unsupervised

Let Features Decide for Themselves: Feature Mask Network for Person Re-identification [abstract]

Excitation Dropout: Encouraging Plasticity in Deep Neural Networks [abstract]

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation [abstract]

Weakly Supervised Salient Object Detection Using Image Labels [abstract]

Learn To Pay Attention [abstract]

Saliency Guided End-to-End Learning for Weakly Supervised Object Detection [abstract]

Self-Erasing Network for Integral Object Attention [abstract]

Adversarial Complementary Learning for Weakly Supervised Object Localization [abstract]

Unsupervised Learning From Video to Detect Foreground Objects in Single Images [abstract]

Tell Me Where to Look: Guided Attention Inference Network [abstract]

Revisiting Dilated Convolution- A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation [abstract]

Segmentation

Conditional random fields

Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [abstract]

Instance-Level Segmentation with Deep Densely Connected MRFs [abstract]

Higher Order Conditional Random Fields in Deep Neural Networks [abstract]

Deepcut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks [abstract]

Fast Semantic Image Segmentation with High Order Context and Guided Filtering [abstract]

Conditional Random Fields As Recurrent Neural Networks [abstract]

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs [abstract]

Discriminative Training of Deep Fully-Connected Continuous CRF with Task-Specific Loss [abstract]

Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network [abstract]

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation [abstract]

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation [abstract]

Deconvolution

Residual Conv-Deconv Grid Network for Semantic Segmentation [abstract]

Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation [abstract]

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation [abstract]

Large Kernel Matters: Improve Semantic Segmentation By Global Convolutional Network [abstract]

ExFuse: Enhancing Feature Fusion for Semantic Segmentation [abstract]

Label Refinement Network for Coarse-to-Fine Semantic Segmentation [abstract]

Pixel Deconvolutional Networks [abstract]

Decoupled Deep Neural Network for Semi-Supervised Semantic Segmentation [abstract]

Fully Convolutional Networks for Semantic Segmentation [abstract]

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks [abstract]

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [abstract]

The One Hundred Layers Tiramisu: Fully Convolutional Densenets for Semantic Segmentation [abstract]

Select, Attend, and Transfer: Light, Learnable Skip Connections [abstract]

Multi-Scale Context Aggregation By Dilated Convolutions [abstract]

Global Deconvolutional Networks for Semantic Segmentation [abstract]

Learning Deconvolution Network for Semantic Segmentation [abstract]

Path Aggregation Network for Instance Segmentation [abstract]

Instance

Shape-Aware Instance Segmentation [abstract]

Associative Embedding-End-to-End Learning for Joint Detection and Grouping [abstract]

MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features [abstract]

A Multipath Network for Object Detection [abstract]

Mask R-CNN [abstract]

Bottom-Up Instance Segmentation Using Deep Higher-Order CRFs [abstract]

Iterative Instance Segmentation [abstract]

Monocular Object Instance Segmentation and Depth Ordering with CNNs [abstract]

Learning to Refine Object Segments [abstract]

Object Detection Free Instance Segmentation with Labeling Transformations [abstract]

Bounding Box Embedding for Single Shot Person Instance Segmentation [abstract]

Semantic Instance Segmentation with a Discriminative Loss Function [abstract]

Fully Convolutional Instance-Aware Semantic Segmentation [abstract]

Instance-Sensitive Fully Convolutional Networks [abstract]

Object Boundary Guided Semantic Segmentation [abstract]

Affinity CNN: Learning Pixel-Centric Pairwise Relations for Figure-Ground Embedding [abstract]

Instance-Aware Semantic Segmentation via Multi-Task Network Cascades [abstract]

Instance-Level Segmentation with Deep Densely Connected MRFs [abstract]

Instance Segmentation by Deep Coloring [abstract]

Semantic Instance Segmentation via Deep Metric Learning [abstract]

Bridging Category-Level and Instance-Level Semantic Image Segmentation [abstract]

Panoptic Segmentation [abstract]

Learning to Segment Object Candidates [abstract]

PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model [abstract]

Pixelwise Instance Segmentation with a Dynamically Instantiated Network [abstract]

Path Aggregation Network for Instance Segmentation [abstract]

Morphology

Flood-Filling Networks [abstract]

Learned Watershed: End-to-End Learning of Seeded Segmentation [abstract]

Reformulating Level Sets As Deep Recurrent Neural Network Approach to Semantic Segmentation [abstract]

Deep Watershed Transform for Instance Segmentation [abstract]

Things and stuff

Panoptic Segmentation [abstract]

Stuffnet: Using 'Stuff' to Improve Object Detection [abstract]

Weakly Supervised Object Localization Using Things and Stuff Transfer [abstract]

Convolutional Feature Masking for Joint Object and Stuff Segmentation [abstract]

COCO-Stuff: Thing and Stuff Classes in Context [abstract]

Video

Weakly-Supervised Semantic Segmentation Using Motion Cues [abstract]

Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning [abstract]

Deep Spatio-Temporal Random Fields for Efficient Video Segmentation [abstract]

One-Shot Video Object Segmentation [abstract]

Learning to Segment Moving Objects [abstract]

Object Detection, Tracking, and Motion Segmentation for Object-Level Video Segmentation [abstract]

Spatio-Temporal Image Boundary Extrapolation [abstract]

Recurrent Fully Convolutional Networks for Video Segmentation [abstract]

Unsupervised Object Segmentation in Video By Efficient Selection of Highly Probable Positive Features [abstract]

Clockwork Convnets for Video Semantic Segmentation [abstract]

Learning Video Object Segmentation with Visual Memory [abstract]

Deep End2End Voxel2Voxel Prediction [abstract]

Weakly-supervised

Transferable Semi-supervised Semantic Segmentation [abstract]

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation [abstract]

Built-in Foreground-Background Prior for Weakly-Supervised Semantic Segmentation [abstract]

Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning [abstract]

Weakly-Supervised Semantic Segmentation Using Motion Cues [abstract]

Learning to Segment Every Thing [abstract]

Learn To Pay Attention [abstract]

Exploiting Saliency for Object Segmentation From Image Level Labels [abstract]

TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection [abstract]

Revisiting Dilated Convolution- A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation [abstract]

Semi-supervised learning

Improving Consistency-Based Semi-Supervised Learning with Weight Averaging [abstract]

DEEP-CARVING: Discovering Visual Attributes By Carving Deep Neural Nets [abstract]

Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination [abstract]

SaaS: Speed as a Supervisor for Semi-supervised Learning [abstract]

Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning [abstract]

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks [abstract]

Labeling the Features not the Samples: Efficient Video Classification with Minimal Supervision [abstract]

Attend in Groups: a Weakly-Supervised Deep Learning Framework for Learning From Web Data [abstract]

Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks [abstract]

Deep Co-Training for Semi-Supervised Image Recognition [abstract]

Geometry/layout

Unsupervised Representation Learning by Predicting Image Rotations [abstract]

DeepPermNet: Visual Permutation Learning [abstract]

Unsupervised Natural Image Patch Learning [abstract]

Unsupervised Holistic Image Generation From Key Local Patches [abstract]

Generalizable Features From Unsupervised Learning [abstract]

Improvements to context based self-supervised learning [abstract]

Invariant Information Distillation for Unsupervised Image Segmentation and Clustering [abstract]

Self-Supervised Video Representation Learning with Odd-One-Out Networks [abstract]

Noisy labels

CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise [abstract]

Seeing Through the Human Reporting Bias: Visual Classifiers From Noisy Human-Centric Labels [abstract]

Learning Deep Visual Object Models From Noisy Web Data: How to Make It Work [abstract]

Learning Deep Networks From Noisy Labels with Dropout Regularization [abstract]

Attend in Groups: a Weakly-Supervised Deep Learning Framework for Learning From Web Data [abstract]

Auxiliary Image Regularization for Deep CNNs with Noisy Labels [abstract]

Learning From Noisy Labels with Distillation [abstract]

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition [abstract]

Iterative Learning with Open-set Noisy Labels [abstract]

Training Deep Neural Networks on Noisy Labels with Bootstrapping [abstract]

On the Resistance of Neural Nets to Label Noise [abstract]

Training Convolutional Networks with Noisy Labels [abstract]

Open-set recognition

Towards Open World Recognition [abstract]

Impostor Networks for Fast Fine-Grained Recognition [abstract]

The Extreme Value Machine [abstract]

Towards Open Set Deep Networks [abstract]

Rethinking Feature Distribution for Loss Functions in Image Classification [abstract]

Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition [abstract]

Online Open World Recognition [abstract]

Adversarial Open-World Person Re-Identification [abstract]

Confidence from Invariance to Image Transformations [abstract]

Iterative Learning with Open-set Noisy Labels [abstract]

Reducing Network Agnostophobia [abstract]

Self-supervised

Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach [abstract]

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks [abstract]

Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination [abstract]

Invariant Information Distillation for Unsupervised Image Segmentation and Clustering [abstract]

Autoconvolution for Unsupervised Feature Learning [abstract]

Unsupervised Object Segmentation in Video By Efficient Selection of Highly Probable Positive Features [abstract]

Unsupervised Learning by Predicting Noise [abstract]

Video

Learning By Tracking: Siamese CNN for Robust Target Association [abstract]

Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video [abstract]

Weakly-Supervised Semantic Segmentation Using Motion Cues [abstract]

Personalizing Human Video Pose Estimation [abstract]

Unsupervised Learning of Visual Representations Using Videos [abstract]

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition [abstract]

Cross Pixel Optical Flow Similarity for Self-Supervised Learning [abstract]

Learning Features By Watching Objects Move [abstract]

Transitive Invariance for Self-supervised Visual Representation Learning [abstract]

Unsupervised learning from videos using temporal coherency deep networks [abstract]

Watch and Learn: Semi-Supervised Learning of Object Detectors From Videos [abstract]

Object-Centric Representation Learning From Unlabeled Videos [abstract]

Learning to Estimate Pose By Watching Videos [abstract]

Shape

3d point clouds

3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks [abstract]

URSA: A Neural Network for Unordered Point Clouds Using Constellations [abstract]

PointConv: Deep Convolutional Networks on 3D Point Clouds [abstract]

PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation [abstract]

SPLATNet: Sparse Lattice Networks for Point Cloud Processing [abstract]

Spherical Convolutional Neural Network for 3D Point Clouds [abstract]

Pointnet: Deep Learning on Point Sets for 3D Classification and Segmentation [abstract]

Tangent Convolutions for Dense Prediction in 3D [abstract]

Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds [abstract]

SO-Net: Self-Organizing Network for Point Cloud Analysis [abstract]

3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds [abstract]

Graph Convolutions on Spectral Embeddings: Learning of Cortical Surface Data [abstract]

3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local Contextual Cues [abstract]

Dynamic Graph CNN for Learning on Point Clouds [abstract]

SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters [abstract]

Point Convolutional Neural Networks by Extension Operators [abstract]

Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space [abstract]

Point-wise Convolutional Neural Network [abstract]

PointCNN [abstract]

Synthesis

Filtering

Dehazenet: an End-to-End System for Single Image Haze Removal [abstract]

A Review of Convolutional Neural Networks for Inverse Problems in Imaging [abstract]

Fast Image Processing with Fully-Convolutional Networks [abstract]

Image Smoothing via Unsupervised Learning [abstract]

Automatic Photo Adjustment Using Deep Learning [abstract]

Chaining Identity Mapping Modules for Image Denoising [abstract]

Learning a Convolutional Neural Network for Non-Uniform Motion Blur Removal [abstract]

DeepISP: Learning End-to-End Image Processing Pipeline [abstract]

Learning to See in the Dark [abstract]

Convolutional Dictionary Learning via Local Processing [abstract]

Fast End-to-End Trainable Guided Filter [abstract]

Inpainting

Context Encoders: Feature Learning By Inpainting [abstract]

Deep Feature Interpolation for Image Content Changes [abstract]

High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis [abstract]

Structural inpainting [abstract]

Style transfer

Neural Style Transfer: A Review [abstract]

Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer [abstract]

A Neural Algorithm of Artistic Style [abstract]

The Contextual Loss for Image Transformation with Non-Aligned Data [abstract]

The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing [abstract]

A Learned Representation for Artistic Style [abstract]

Preserving Color in Neural Artistic Style Transfer [abstract]

Stylebank: an Explicit Representation for Neural Image Style Transfer [abstract]

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization [abstract]

Demystifying Neural Style Transfer [abstract]

Controlling Perceptual Factors in Neural Style Transfer [abstract]

Super-resolution

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [abstract]

Convolutional Networks with Muxout Layers As Multi-Rate Systems for Image Upscaling [abstract]

Deep Image Prior [abstract]

Self-Tuned Deep Super Resolution [abstract]

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network [abstract]

Pixel Recursive Super Resolution [abstract]

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution [abstract]

Image Super-Resolution Using Deep Convolutional Networks [abstract]

Text

Deep Structured Output Learning for Unconstrained Text Recognition [abstract]

Textboxes: A Fast Text Detector with a Single Deep Neural Network [abstract]

Decomposition-Based Domain Adaptation for Real-World Font Recognition [abstract]

Reading Text in the Wild with Convolutional Neural Networks [abstract]

Deeptext: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images [abstract]

Image captioning

Sequence to Sequence: Video to Text [abstract]

Seeing Through the Human Reporting Bias: Visual Classifiers From Noisy Human-Centric Labels [abstract]

Learning to Generalize to New Compositions in Image Understanding [abstract]

Neural Baby Talk [abstract]

The Long-Short Story of Movie Description [abstract]

Generating Multi-Sentence Lingual Descriptions of Indoor Scenes [abstract]

Stories in the Eye: Contextual Visual Interactions for Efficient Video to Language Translation [abstract]

Ask Your Neurons: A Neural-Based Approach to Answering Questions About Images [abstract]

Densecap: Fully Convolutional Localization Networks for Dense Captioning [abstract]

Deep Visual-Semantic Alignments for Generating Image Descriptions [abstract]

Grounding Visual Explanations [abstract]

Fisher Vectors Derived From Hybrid Gaussian-Laplacian Mixture Models for Image Annotation [abstract]

Deep Captioning with Multimodal Recurrent Neural Networks (M-RNN) [abstract]

Visual question answering

iVQA: Inverse Visual Question Answering [abstract]

Visual Madlibs: Fill in the Blank Image Generation and Question Answering [abstract]

Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition [abstract]

Solving Visual Madlibs with Multiple Cues [abstract]

Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning [abstract]

Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool [abstract]

Tracking

Learning By Tracking: Siamese CNN for Robust Target Association [abstract]

Online Tracking By Learning Discriminative Saliency Map with Convolutional Neural Network [abstract]

First Step Toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks [abstract]

Learning to Track at 100 FPS with Deep Regression Networks [abstract]

Fully-Convolutional Siamese Networks for Object Tracking [abstract]

Deeptrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking [abstract]

VideoMatch: Matching based Video Object Segmentation [abstract]

Robust Tracking via Convolutional Networks Without Learning [abstract]

Transferring Rich Feature Hierarchies for Robust Visual Tracking [abstract]

Siamese Instance Search for Tracking [abstract]

On the Performance of Convnet Features for Place Recognition [abstract]

Learning to Track for Spatio-Temporal Action Localization [abstract]

Online Domain Adaptation for Multi-Object Tracking [abstract]

Once for All: a Two-Flow Convolutional Neural Network for Visual Tracking [abstract]

Prediction

TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents [abstract]

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks [abstract]

Predicting Future Instance Segmentations by Forecasting Convolutional Features [abstract]

One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network [abstract]

SDCNet: Video Prediction Using Spatially-Displaced Convolution [abstract]

Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning [abstract]

Predicting the Future with Transformational States [abstract]

Video Time: Properties, Encoders and Evaluation [abstract]

Visualization

Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks [abstract]

Understanding Neural Networks Through Deep Visualization [abstract]

Interpreting Deep Visual Representations via Network Dissection [abstract]

Visualizing and Understanding Convolutional Neural Networks [abstract]

Axiomatic Attribution for Deep Networks [abstract]

Explaining the Unexplained: A Class-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks [abstract]

Visualizing and Comparing Convolutional Neural Networks [abstract]

Towards Better Analysis of Deep Convolutional Neural Networks [abstract]

SmoothGrad: removing noise by adding noise [abstract]

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis [abstract]

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps [abstract]

Striving for Simplicity: the All Convolutional Net [abstract]

Understanding Intra-Class Knowledge Inside CNN [abstract]

Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks [abstract]

A New Method to Visualize Deep Neural Networks [abstract]