← Search

Kei Akuzawa

2 accepted papers

2020

Stabilizing Adversarial Invariance Induction from Divergence Minimization Perspective

IJCAI 2020poster

Adversarial invariance induction (AII) is a generic and powerful framework for enforcing an invariance to nuisance attributes into neural network representations. However, its optimization is often unstable and little is known about its practical behavior. This paper presents an analysis of the reas…