Vision Transformer with Deformable Attention
Zhuofan Xia, Xuran Pan, Shiji Song et al.
2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 848 citations
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply enlarging receptive field also gives rise to several concerns. On the one hand, using dense attention e.g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests. On the other hand, the sparse attention adopted in PVT or Swin Transformer is data agnostic and may l…
Explore this paper's citation graph on Constellation.