Shape-Texture Debiased Neural Network Training

Abstract

Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. Our ablation shows that such bias degenerates model performance. Motivated by this observation, we develop a simple algorithm for shape-texture debiased learning. To prevent models from exclusively attending on a single cue in representation learning, we augment training data with images with conflicting shape and texture information (eg, an image of chimpanzee shape but with lemon texture) and, most importantly, provide the corresponding supervisions from shape and texture simultaneously. Experiments show that our method successfully improves model performance on several image recognition benchmarks and adversarial robustness. For example, by training on ImageNet, it helps ResNet-152 achieve substantial improvements on ImageNet (+1.2%), ImageNet-A (+5.2%), ImageNet-C (+8.3%) and Stylized-ImageNet (+11.1%), and on defending against FGSM adversarial attacker on ImageNet (+14.4%). Our method also claims to be compatible with other advanced data augmentation strategies, eg, Mixup, and CutMix. The code is available here: https://github.com/LiYingwei/ShapeTextureDebiasedTraining.

ICLR 2021. The code is available here: https://github.com/LiYingwei/ShapeTextureDebiasedTraining

References in corpus (12)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Shortcut Learning in Deep Neural Networks
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Learning Robust Global Representations by Penalizing Local Predictive Power
• Fast Patch-based Style Transfer of Arbitrary Style
• Natural Adversarial Examples
• Style-Transfer via Texture-Synthesis
• Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
• Robust and Accurate Object Detection via Adversarial Learning

Cited by in corpus (4)

• On Feature Normalization and Data Augmentation
• Robust and Accurate Object Detection via Adversarial Learning
• Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
• White Paper Assistance: A Step Forward Beyond the Shortcut Learning