Self-Challenging Improves Cross-Domain Generalization

August 2020

Self-Challenging Improves Cross-Domain Generalization

Authors:

Zeyi Huang, Haohan Wang, Eric P. Xing, and Dong Huang
Conference Paper
Proceedings of (ECCV) European Conference on Computer Vision

Abstract:

Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar distributions, their dominant features are similar, leading to decent test performance. The performance is nonetheless unmet when tested with different distributions, leading to the challenges in cross-domain image classification. We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges (discards) the dominant features activated on the training data, and forces the network to activate remaining features that correlate with labels. This process appears to activate feature representations applicable to out-of-domain data without prior knowledge of the new domain and without learning extra network parameters. We present the theoretical properties and conditions of RSC for improving cross-domain generalization. The experiments endorse the simple, effective, and architecture-agnostic nature of our RSC method.
@conference{Huang-2020-123146,
author = {Zeyi Huang And Haohan Wang And Eric P. Xing And Dong Huang},
title = {Self-Challenging Improves Cross-Domain Generalization},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2020},
month = {August},
keywords = {cross-domain generalization, robustness},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.