Timezone: »

 
Poster
Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
Baifeng Shi · Dinghuai Zhang · Qi Dai · Zhanxing Zhu · Yadong Mu · Jingdong Wang

Tue Jul 14 08:00 AM -- 08:45 AM & Tue Jul 14 07:00 PM -- 07:45 PM (PDT) @
in Poster Session 2 »

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. Code is available at https://github.com/bfshi/InfoDrop.

Keywords: Algorithms · Computer Vision · Representation Learning · Accountability, Transparency and Interpretability

Author Information

Baifeng Shi (Peking University)
Dinghuai Zhang (Peking University)
Qi Dai (Microsoft Research)
Zhanxing Zhu (Peking University)
Yadong Mu (Peking University)
Jingdong Wang (Microsoft)

More from the Same Authors