Representation Learning (MVA)

Title: Representation Learning for Computer Vision and Medical Imaging

Instructors: Pietro Gori and Loïc Le Folgoc

Objectives and Topics: Good and expressive data representations can improve the accuracy of machine learning problems and ease interpretability and transfer. For computer vision and medical imaging tasks, handcrafting good data representations, a.k.a. feature engineering, was traditionally hard. Deep Learning has changed this paradigm by allowing the automatic discovery of good representations from data. This is known as representation learning. The objective of this course is to provide an introduction to representation learning in computer vision and medical imaging applications. We will cover the following topics:

• Representation Learning
• Transfer Learning
• Domain Adaptation
• Multi-task Learning
• Knowledge Distillation
• Self-Supervised Learning and Foundation models
• Attention and Transformers
• Disentangled Representations using Generative Models
• Uncertainty, Interpretability and Explainability in Neural Networks

Validation: Grading will be based on the practical session reports (50%) and written or oral exam (depending on the number of students) (50%).

Language: English or French (depending on the audience)

Organization: 8 lectures divided into 1,5h of theory and 1,5h of practical session + 1 session of exam

Location: All lectures and practical sessions will be held at Télécom Paris. Please bring your own laptop

Lectures: