Invertible Neural Networks and Inverse Problems

Online lecture on Invertible Neural Networks as priors for inverse problems in imaging. This lecture is from Northeastern University's CS 7180 Spring 2020 class on Special Topics in Artificial Intelligence, taught by Paul Hand.
The notes are available at: khoury.northeas...
The papers mentioned are:
NICE - Laurent Dinh, David Krueger, and Yoshua Bengio. "Nice: Non-linear independent components estimation." arxiv.org/abs/...
Real-NVP - Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. "Density estimation using real nvp." arxiv.org/abs/...
Glow - Diederik Kingma, and Prafulla Dhariwal. "Glow: Generative flow with invertible 1x1 convolutions." In Advances in Neural Information Processing Systems, pp. 10215-10224. 2018. arxiv.org/abs/...
Asim et al. - Muhammad Asim, Ali Ahmed, and Paul Hand. "Invertible generative models for inverse problems: mitigating representation error and dataset bias." arxiv.org/abs/...
Whang et al. - Jay Whang, Qi Lei, and Alexandros G. Dimakis. "Compressed Sensing with Invertible Generative Models and Dependent Noise." arxiv.org/abs/...
Ardizzone et al. - Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, and Ullrich Köthe. "Analyzing inverse problems with invertible neural networks." arxiv.org/abs/...

[@JTMoustache]

If anyone is wondering how they thought about these architectures, look at the Feistel Network in cryptography- not sure if they reference it in their paper, but that’s definitely how they got the insight.

[@GermanTutorials]

Excellent review of this topic! Thank you very much!

[@amirm7373]

Stunning review!

[@haolibai7503]

impressive. THANKS

[@s4life91]

great video

[@modernsolutions6631]

Viewer nr. 10000