Self-Supervised Dynamic Networks for Covariate Shift Robustness
Abstract
As supervised learning still dominates most AI applications, test-time performance is often unexpected. Specifically, a shift of the input covariates, caused by typical nuisances like background-noise, illumination variations or transcription errors, can lead to a significant decrease in prediction accuracy. Recently, it was shown that incorporating self-supervision can significantly improve covariate shift robustness. In this work, we propose Self-Supervised Dynamic Networks (SSDN): an input-dependent mechanism, inspired by dynamic networks, that allows a self-supervised network to predict the weights of the main network, and thus directly handle covariate shifts at test-time. We present the conceptual and empirical advantages of the proposed method on the problem of image classification under different covariate shifts, and show that it significantly outperforms comparable methods.
Cite
@article{arxiv.2006.03952,
title = {Self-Supervised Dynamic Networks for Covariate Shift Robustness},
author = {Tomer Cohen and Noy Shulman and Hai Morgenstern and Roey Mechrez and Erez Farhan},
journal= {arXiv preprint arXiv:2006.03952},
year = {2020}
}