pith. sign in

arxiv: 2201.00520 · v3 · pith:JX5XP2QHnew · submitted 2022-01-03 · 💻 cs.CV

Vision Transformer with Deformable Attention

classification 💻 cs.CV
keywords attentiondeformabletransformerself-attentiondensefeaturesfieldhand
0
0 comments X
read the original abstract

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 limit the ability to model long range relations. To mitigate these issues, we propose a novel deformable self-attention module, where the positions of key and value pairs in self-attention are selected in a data-dependent way. This flexible scheme enables the self-attention module to focus on relevant regions and capture more informative features. On this basis, we present Deformable Attention Transformer, a general backbone model with deformable attention for both image classification and dense prediction tasks. Extensive experiments show that our models achieve consistently improved results on comprehensive benchmarks. Code is available at https://github.com/LeapLabTHU/DAT.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder

    cs.CV 2026-06 unverdicted novelty 6.0

    IDEAL improves discrete representation autoencoders by jointly aligning quantized tokens with shallow and deep VFM features, reporting 0.61 rFID on ImageNet and 1.89 gFID for autoregressive image generation.

  2. BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 5.0

    BEVPredFormer uses attention-based temporal processing and 3D camera projection to match or exceed prior methods on nuScenes for BEV instance prediction.