This half-day CVPR 2021 tutorial will cover Normalizing Flows and Invertible Neural Networks with a specific focus on applications in computer vision.
Normalizing flows (NFs) offer an answer to a long-standing question in computer vision: How can one define faithful probabilistic models for complex high-dimensional data like natural images? NFs solve this problem by means of non-linear bijective mappings from simple distributions (e.g. multivariate normal) to the desired target distributions. These mappings are implemented with invertible neural networks and thus have high expressive power and can be trained by gradient descent in the usual way. Thanks to bijectivity, NFs can work forward and backward, serving as both discriminative and generative models alike, and are especially suitable for inverse problems. This tutorial will explain the theoretical underpinnings of NFs, show various practical implementation options, clarify their relationships with GANs, VAEs, and non-linear ICA. Particular emphasis will be given to successful applications in the field of computer vision.
The tutorial is intended to be introductory, i.e., aimed at people with basic backgrounds in ML/CV who are interested in applying these methods in related problems.
- Normalizing Flows: An Introduction and Review of Current Methods by Ivan Kobyzev, Simon J.D. Prince and Marcus A. Brubaker. IEEE PAMI, 2020.