English

TransforMatcher: Match-to-Match Attention for Semantic Correspondence

Computer Vision and Pattern Recognition 2022-05-25 v1

Abstract

Establishing correspondences between images remains a challenging task, especially under large appearance changes due to different viewpoints or intra-class variations. In this work, we introduce a strong semantic image matching learner, dubbed TransforMatcher, which builds on the success of transformer networks in vision domains. Unlike existing convolution- or attention-based schemes for correspondence, TransforMatcher performs global match-to-match attention for precise match localization and dynamic refinement. To handle a large number of matches in a dense correlation map, we develop a light-weight attention architecture to consider the global match-to-match interactions. We also propose to utilize a multi-channel correlation map for refinement, treating the multi-level scores as features instead of a single score to fully exploit the richer layer-wise semantics. In experiments, TransforMatcher sets a new state of the art on SPair-71k while performing on par with existing SOTA methods on the PF-PASCAL dataset.

Keywords

Cite

@article{arxiv.2205.11634,
  title  = {TransforMatcher: Match-to-Match Attention for Semantic Correspondence},
  author = {Seungwook Kim and Juhong Min and Minsu Cho},
  journal= {arXiv preprint arXiv:2205.11634},
  year   = {2022}
}

Comments

Accepted to CVPR 2022 (poster presentation)

R2 v1 2026-06-24T11:26:16.943Z