Reading group in Pattern Recognition and Computer Vision

Login to KOS for course enrollment Display time-table
Code Completion Credits Range Language
XP33RCV ZK 4 2P+2S English
Georgios Tolias
Georgios Tolias
Department of Cybernetics

The course deals with fundamental results from computer vision and

pattern recognition. The course treats selected key

results, as well as latest areas of research, especially those

which substantially influence the development in the subject field.

Education is performed in the form of a reading group.



Syllabus of lectures:

There are no standard lectures.

Syllabus of tutorials:

The selected topics and terms of the reading groups will be announced at http://cmp.felk.cvut.cz/~toliageo/rg/ .

The course lasts two semesters with approximately 1 reading group per month.

Each student is expected to come prepared to reading groups, with knowledge of the presented paper, and to prepare the presentation (1 hour long) of a paper.

Study Objective:

Using topics from pattern recognition and computer vision, teach students how to work with literature and present scientific results both orally and in a written form.

Study materials:

Below is a sample list of suggested papers that are appropriate for a reading group. Such a list if maintained in http://cmp.felk.cvut.cz/~toliageo/rg/suggested.html

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, ECCV 2020

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval, Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman, ECCV 2020

Learning Feature Descriptors using Camera Pose Supervision, Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, and Noah Snavely, ECCV 2020

Momentum Contrast for Unsupervised Visual Representation Learning, Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick, arxiv 2019

Deep Declarative Networks: A New Hope, Stephen Gould, Richard Hartley, Dylan Campbell, arxiv 2019

LCA: Loss Change Allocation for Neural Network Training, J. Lan, R. Liu, H. Zhou, J. Yosinski, NeurIPS 2019

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, A. Tarvainen, H. Valpola, NeurIPS 2017

in combination with other approaches for consistency loss, such as:

Mutual exclusivity loss for semi-supervised deep learning, Mehdi Sajjadi, Mehran Javanmardi, and Tolga Tasdizen. ICIP 2016.


Temporal ensembling for semi-supervised learning, S. Laine and T. Aila. ICLR 2017.

mixup: BEYOND EMPIRICAL RISK MINIMIZATION. H. Zhang, M. Cisse, Y. Dauphin, D. Lopez-Paz, ICLR 2018

together with

Manifold Mixup: Better Representations by Interpolating Hidden States. V. Verma, A. Lamb, C. Beckham, A. Najafi, I. Mitliagkas, A. Courville, D. Lopez-Paz, Y. Bengio , ICML 2019

LaSO: Label-Set Operations networks for multi-label few-shot learning, A. Alfassy, L. Karlinsky, A. Aides, J. Shtok, S. Harary, R. Feris, CVPR 2019

Time-table for winter semester 2020/2021:
Time-table is not available yet
Time-table for summer semester 2020/2021:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2020-09-23
For updated information see http://bilakniha.cvut.cz/en/predmet6019906.html