Shunted Self-Attention via Multi-Scale Token Aggregation
arXiv:2111.15193
Abstract
Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models, however, usually designate the similar receptive fields of each token feature within each layer. Such a constraint inevitably limits the ability of each self-attention layer in capturing multi-scale features, thereby leading to performance degradation in handling images with multiple objects of different scales. To address this issue, we propose a novel and generic strategy, termed shunted self-attention~(SSA), that allows ViTs to model the attentions at hybrid scales per attention layer. The key idea of SSA is to inject heterogeneous receptive field sizes into tokens: before computing the self-attention matrix, it selectively merges tokens to represent larger object features while keeping certain tokens to preserve fine-grained features. This novel merging scheme enables the self-attention to learn relationships between objects with different sizes and simultaneously reduces the token numbers and the computational cost. Extensive experiments across various tasks demonstrate the superiority of SSA. Specifically, the SSA-based transformer achieves 84.0\% Top-1 accuracy and outperforms the state-of-the-art Focal Transformer on ImageNet with only half of the model size and computation cost, and surpasses Focal Transformer by 1.3 mAP on COCO and 2.9 mIOU on ADE20K under similar parameter and computation cost. Code has been released at https://github.com/OliverRensu/Shunted-Transformer.
CVPR2022 Oral
References in corpus (9)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- PVT v2: Improved Baselines with Pyramid Vision Transformer
- Transformer in Transformer
- DeepViT: Towards Deeper Vision Transformer
- Focal Self-attention for Local-Global Interactions in Vision Transformers
- LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
- CMT: Convolutional Neural Networks Meet Vision Transformers
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
- Co-advise: Cross Inductive Bias Distillation