English

Vision Transformer with Key-select Routing Attention for Single Image Dehazing

Computer Vision and Pattern Recognition 2024-07-01 v1

Abstract

We present Ksformer, utilizing Multi-scale Key-select Routing Attention (MKRA) for intelligent selection of key areas through multi-channel, multi-scale windows with a top-k operator, and Lightweight Frequency Processing Module (LFPM) to enhance high-frequency features, outperforming other dehazing methods in tests.

Cite

@article{arxiv.2406.19703,
  title  = {Vision Transformer with Key-select Routing Attention for Single Image Dehazing},
  author = {Lihan Tong and Weijia Li and Qingxia Yang and Liyuan Chen and Peng Chen},
  journal= {arXiv preprint arXiv:2406.19703},
  year   = {2024}
}

Comments

5 pages,4 figures,IEICE Trans. Information and Systems

R2 v1 2026-06-28T17:22:18.177Z