Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

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

Accepted to ICML2020. Code is available at https://github.com/bfshi/InfoDrop

Cited by in corpus (12)

• Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
• Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR
• Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
• Robust and Generalizable Visual Representation Learning via Random Convolutions
• Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
• A Fourier-based Framework for Domain Generalization
• Shape-Texture Debiased Neural Network Training
• Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
• Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
• Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs
• Combining Diverse Feature Priors
• White Paper Assistance: A Step Forward Beyond the Shortcut Learning