All about practicals: Here
Course 1 (Sept. 24, 2025)
- Introduction to Computer Vision and ML basics slides1
- Visual (local) feature detection and description
Bag of Word Image representation
Course 2
Linear classification (SVM) slides2_SVM
Introduction to Neural Networks (NNs) slides2_NN
Course 3
NN training and Statistical decision theory slides3_NN
Datasets, benchmarks and evaluation slides3_DATA
Course 4
Neural Nets for Image Classification slides4_LargeConvNet
Course 5
Large Neural Nets for Image Classification slides5_LargeConvNet
Vision Transformers slides_vit1
Course 6:
Complements for intialization of NNs and normalization: BatchNorm, LayerNorm (convnet or transformer), InstanceNorm
Details of Vision Transformers architecture: Embedding matrix, positional encoding, attention module, FFN module, Norms, classToken, …
Course 7
Segmentation with CNN slides_segmenta
Transfer learning and Domain adaptation slides7_Transfer
Course 8
Generative models with GANs slides8.pdf
Course 9
Conditional GANs and Diffusion models slides9.pdf
Course 10
Vision-Language models slides10.pdf
Course 11 (Jan. 07)
Control 2pm-3:45pm + practicals 4pm-6pm
Course 12 Diffusion models for Image Generation (Alasdair)
Course 13 Bayesian deep learning (Clement)
Course 14 Failure and ood detection (Clement)
Further reading (available at SorbonneU library):
Book Pattern Recognition and Machine Learning, C. M. Bishop
Book Deep Learning, I. Goodfellow, Y. Bengio, A. Courville
Book Computer Vision: Algorithms and Applications, Richard Szeliski