Informative dropout for robust representation learning: a shape-bias perspective

Shi, Baifeng, Zhang, Dinghuai, Dai, Qi, Zhu, Zhanxing, Mu, Yadong and Wang, Jingdong (2020) Informative dropout for robust representation learning: a shape-bias perspective. Daumé, Hal and Singh, Aarti (eds.) In ICML'20: Proceedings of the 37th International Conference for Machine Learning (ICML). International Machine Learning Society. 8828–8839 . (doi:10.5555/3524938.3525757).

Abstract

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN's texture-bias and its robustness against distribution shift, adversarial perturbation, random corruption, etc. In this work, we attempt at improving various kinds of robustness universally by alleviating CNN's texture bias. With inspiration from the human visual system, we propose a light-weight model-agnostic method, namely Informative Dropout (InfoDrop), to improve interpretability and reduce texture bias. Specifically, we discriminate texture from shape based on local self-information in an image, and adopt a Dropout-like algorithm to decorrelate the model output from the local texture. Through extensive experiments, we observe enhanced robustness under various scenarios (domain generalization, few-shot classification, image corruption, and adversarial perturbation). To the best of our knowledge, this work is one of the earliest attempts to improve different kinds of robustness in a unified model, shedding new light on the relationship between shape-bias and robustness, also on new approaches to trustworthy machine learning algorithms.

This record has no associated files available for download.

Contributors

Download statistics