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.
|
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s11263-022-01602-y | International Journal of Computer Vision |
Keywords | DocType | Volume |
Semantic Correspondence, Image-level Contrastive Learning, Pixel-level Contrastive Learning, Cross-instance Cycle Consistency | Journal | 130 |
Issue | ISSN | Citations |
5 | 0920-5691 | 0 |
PageRank | References | Authors |
0.34 | 5 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taihong Xiao | 1 | 10 | 3.30 |
Sifei Liu | 2 | 227 | 17.54 |
Shalini Gupta | 3 | 299 | 20.42 |
Zhiding Yu | 4 | 421 | 30.08 |
Jan Kautz | 5 | 3615 | 198.77 |
Yang Ming-Hsuan | 6 | 15303 | 620.69 |