Understanding Classifiers with Generative Models

no code implementations • 1 Jan 2021 • Laëtitia Shao, Yang song, Stefano Ermon

Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle.

Two-sample testing

Understanding Classifier Mistakes with Generative Models

no code implementations • 5 Oct 2020 • Laëtitia Shao, Yang song, Stefano Ermon

From this observation, we develop a detection criteria for samples on which a classifier is likely to fail at test time.

Two-sample testing

Neighbourhood Distillation: On the benefits of non end-to-end distillation

no code implementations • 2 Oct 2020 • Laëtitia Shao, Max Moroz, Elad Eban, Yair Movshovitz-Attias

Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighbourhoods - that are then trained independently.

Knowledge Distillation Neural Architecture Search