This course studies learning visual representations for common computer vision tasks including matching, retrieval, classification, and object detection. Related problems are discussed including indexing, nearest neighbor search, clustering, and dimensionality reduction. The course discusses well-known methods from low-level description to intermediate representation, and their dependence on the end task. It then studies a data-driven approach where the entire pipeline is optimized jointly in a supervised fashion, according to a task-dependent objective. Deep learning models are studied in detail and interpreted in connection to conventional models. The focus of the course is on recent, state of the art methods and large scale applications.
The course is part of master program Research in Computer Science (SIF) of University of Rennes 1.
The following refers to the first iteration of the course in Nov. 2017 - Jan. 2018.
| Event | Date | Room | Description | Material* |
|---|---|---|---|---|
| Lecture 1 | Monday Nov 20 |
B02B-E110 (23) |
Introduction Research field. Neuroscience, computer vision and machine learning background. Modern deep learning. About this course. |
[slides] |
| Lecture 2 | Wednesday Nov 22 |
B12D i-59 (44) |
Representation Global/local visual descriptors, dense/sparse representation, feature detectors. Encoding/pooling, vocabularies, bag-of-words. Match kernels, embedding, Fisher vectors, VLAD. |
[slides] |
| Lecture 3 | Monday Nov 27 |
B12D i-58 (44) |
Matching Spatial matching, geometric models, RANSAC, Hough transform. Pyramid matching, spatial and Hough pyramids. Object detection, subwindow search, Hough model, deformable part model. |
[slides] |
| Lecture 4 | Wednesday Dec 6 |
B12D i-58 (44) |
Indexing Clustering, dimensionality reduction, density estimation, nearest neighbor search. Tree-based methods, hashing, product quantization. Inverted index and multi-index. |
[slides] |
| Lecture 5 | Monday Dec 11 |
B12D i-59 (44) |
Learning Naive Bayes, nearest neighbor classification. Regression, classification. Logistic regression, support vector machines, neural networks. Activation functions, loss functions, gradient descent. |
[slides] |
| Lecture 6 | Wednesday Dec 13 |
B12D i-58 (44) |
Differentiation Computational graphs, back-propagation, automatic differentiation. |
[slides] |
| Lecture 7 | Monday Dec 18 |
B12D i-58 (44) |
Convolution Pooling, strided convolution, dilated convolution. Convolutional networks. Deconvolution, fully convolutional networks. |
[slides] |
| Milestone | Tuesday Dec 19 |
Oral presentation Selection of papers to present. |
[instructions] | |
| Lecture 8 | Wednesday Jan 10 |
B12D i-58 (44) |
Optimization Parameter initialization, data-dependent initialization, normalization, regularization. Optimization methods, second-order methods, Hessian-free methods. |
[slides] |
| Lecture 9 | Monday Jan 15 |
B12D i-52 (44) |
Detection Class-agnostic region proposals, bounding box regression, non-maxima suppression, part-based models, spatial transformers, attention networks. |
[slides] |
| Lecture 10 | Monday Jan 22 |
B12D i-52 (44) |
Retrieval Siamese, triplet, and batch-wise loss functions. Embedding, pooling, dimensionality reduction and manifold learning. Partial matching, spatial matching, quantization, diffusion. |
[slides] |
| Evaluation 1 | Wednesday Jan 24 |
B12D i-58 (44) | Written exam | |
| Evaluation 2 | Monday Jan 29 |
Jersey |
Oral presentations 08:00 - 12:00 |
[instructions] |
*All material licensed CC BY-SA 4.0