2022-04-05 更新
Improving Vision Transformers by Revisiting High-frequency Components
Authors:Jiawang Bai, Li Yuan, Shu-Tao Xia, Shuicheng Yan, Zhifeng Li, Wei Liu
The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies on the large-scale training set. To explain this observation we make a hypothesis that ViT models are less effective in capturing the high-frequency components of images than CNN models, and verify it by a frequency analysis. Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new frequency perspective, and find that the success of some techniques (e.g., RandAugment) can be attributed to the better usage of the high-frequency components. Then, to compensate for this insufficient ability of ViT models, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models (e.g., +1.2% for ViT-B, +0.5% for Swin-B), and especially enhance the advanced model VOLO-D5 to 87.3% that only uses ImageNet-1K data, and the superiority can also be maintained on out-of-distribution data and transferred to downstream tasks.
PDF 18 pages, 7 figures
论文截图
Discrete Representations Strengthen Vision Transformer Robustness
Authors:Chengzhi Mao, Lu Jiang, Mostafa Dehghani, Carl Vondrick, Rahul Sukthankar, Irfan Essa
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on ImageNet are overly reliant on local textures and fail to make adequate use of shape information. ViTs thus have difficulties generalizing to out-of-distribution, real-world data. To address this deficiency, we present a simple and effective architecture modification to ViT’s input layer by adding discrete tokens produced by a vector-quantized encoder. Different from the standard continuous pixel tokens, discrete tokens are invariant under small perturbations and contain less information individually, which promote ViTs to learn global information that is invariant. Experimental results demonstrate that adding discrete representation on four architecture variants strengthens ViT robustness by up to 12% across seven ImageNet robustness benchmarks while maintaining the performance on ImageNet.
PDF
论文截图