We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Learning Contrastive Representation for Semantic Correspondence.
- Authors
Xiao, Taihong; Liu, Sifei; De Mello, Shalini; Yu, Zhiding; Kautz, Jan; Yang, Ming-Hsuan
- Abstract
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling pixel-level dense correspondences is labor intensive and infeasible to scale. Most existing methods focus on designing various matching modules using fully-supervised ImageNet pretrained networks. On the other hand, while a variety of self-supervised approaches are proposed to explicitly measure image-level similarities, correspondence matching the pixel level remains under-explored. In this work, we propose a multi-level contrastive learning approach for semantic matching, which does not rely on any ImageNet pretrained model. We show that image-level contrastive learning is a key component to encourage the convolutional features to find correspondence between similar objects, while the performance can be further enhanced by regularizing cross-instance cycle-consistency at intermediate feature levels. Experimental results on the PF-PASCAL, PF-WILLOW, and SPair-71k benchmark datasets demonstrate that our method performs favorably against the state-of-the-art approaches.
- Subjects
IMAGE registration; PIXELS
- Publication
International Journal of Computer Vision, 2022, Vol 130, Issue 5, p1293
- ISSN
0920-5691
- Publication type
Article
- DOI
10.1007/s11263-022-01602-y