Shape-Texture Debiased Neural Network Training

By Yingwei Li, Qihang Yu, Mingxing Tan, Jieru Mei, Peng Tang, Wei Shen, Alan L. Yuille, Cihang Xie. 2020

127 citations recorded by the source corpus.

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 (e.g., 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 to other advanced data augmentation strategies, e.g., Mixup and CutMix. The code is available here: https://github.com/LiYingwei/ShapeTextureDebiasedTraining.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yuan He
2. Gege Qi
3. Ranjie Duan
4. Hui Xue
5. Xiaofeng Mao
6. Xiaodan Li
7. Shaokai Ye
8. YueFeng Chen

In Computer Vision and Pattern Recognition

1. Yuan He
2. Gege Qi
3. Ranjie Duan
4. Hui Xue
5. K. Morrison
6. Xiaofeng Mao
7. Colton Lipchak
8. Adam Mattioli

Citations in the corpus

• Towards Robust Vision Transformer (2021, background): “, stronger data augmentation [16, 18, 33], carefully designed [36,44] or searched [9,13] network architecture, improved training strategy [22, 26, 47], quantization [24] and pruning [49] of the weights, better pooling [41, 53] or activation functions [46], etc.”
• Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers (2021, methodology): “An alternative approach explains an algorithm for shapetexture debiased learning by augmenting images in the training set with conflicting shapes and textures (Li et al., 2021).”