# Learning Contrastive Representation for Semantic Correspondence

Source: [Learning Contrastive Representation for Semantic Correspondence](<https://www.sota2.com/research/paper/68fa6bf31e209131cea31261>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:59:56.170Z

Authors: Taihong Xiao, Sifei Liu, Shalini De Mello, Zhiding Yu, Jan Kautz, Ming-Hsuan Yang

Published: 2021-09-22T18:34:14.000Z

## 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 approaches focus on designing various matching approaches with 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. The source code and trained models will be made available to the public.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.10967>)

[PDF](<https://arxiv.org/pdf/2109.10967.pdf>)