Bloc 1 Basics for Visual understanding

18/9 Course 1: Visual Representation of images BoF and BoW

25/9 Course 2: Visual classification (1): Tasks, Datasets, (Linear) classification (SVM)

02/10 Course 3: Visual classification (2): benchmarks and evaluation, Use-Case for BoW

TME 1-2-3 (see docs) on SIFT descriptors, image representation and image classification

Research Papers:

Visual Word Ambiguity, J.C. van Gemert et al.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories, S. Lazebnik
Pooling in Image Representation: the Visual Codeword Point of View, Avila et al.
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features, Grauman & Darrell

Bloc 2 Deep learning for visual understanding

9/10 Course 4: deep (1) Neural Nets for image classification
+ course 3: end of Beyond BoW

16/10 Course 5: deep (2) Convolutional Neural Nets for image classification

23/10 Course 6: deep (3) Large Convolutional Neural Nets for image classification

06/11 Course 7: deep (4) Fully ConvNets for image classification and localization and Transfer learning

20/11 PAS D EXAM

27/11 Course 8: deep (5) Generative models GAN

04/12 Course 9: deep (6) Generative models GAN (2)

11/12 Course 10: deep (7) Detection, Segmentation

18/12 Course 11: Cours annulé et contrôle reporté au 15 janvier 2020 – TP deep (8) maintenu

Bloc 3 advanced deep learning for image understanding

Course ressources

8/1: Course 12: Bayesian Models

15/1: Course 13: CONTROLE COURS exemple exam2018 + Bayesian Neural Networks – TP Bayesian deep nets for classification

22/1: Course14: Bayesian Deep Learning and Robustness

Further reading

Books available at SU library:
Book Pattern Recognition and Machine Learning, C. M. Bishop
Book Machine Learning Techniques for Multimedia, M. Cord, P. Cunningham (Eds.)
Book Deep Learning, I. Goodfellow, Y. Bengio, A. Courville
Book Computer Vision: Algorithms and Applications, Richard Szeliski