Papers › Exploring Localization for Self-supervised Fine-grained Contrastive Learning

Exploring Localization for Self-supervised Fine-grained Contrastive Learning

30 Jun 2021arXiv:2106.15788archive 2025-07-28

Di wu, Siyuan Li, Zelin Zang, Stan Z. Li

Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for fine-grained scenarios is not fully explored. We point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object. Analysis suggests that learning to extract discriminative texture information and localization are equally crucial for fine-grained self-supervised pre-training. Based on our findings, we introduce cross-view saliency alignment (CVSA), a contrastive learning framework that first crops and swaps saliency regions of images as a novel view generation and then guides the model to localize on foreground objects via a cross-view alignment loss. Extensive experiments on both small- and large-scale fine-grained classification benchmarks show that CVSA significantly improves the learned representation.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Westlake-AI/openmixup officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningFine-Grained Image ClassificationFine-Grained Image RecognitionImage ClassificationObject Detectionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification CUB-200-2011 BYOL+CVSA (ResNet-50) Accuracy 77.1 #29 of 30 Archive leaderboard report
Fine-Grained Image Classification FGVC Aircraft BYOL+CVSA (ResNet-50) Accuracy 87.27 #51 of 57 Archive leaderboard report
Fine-Grained Image Classification NABirds BYOL+CVSA (ResNet-50) Accuracy 79.64% #29 of 30 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars BYOL+CVSA (ResNet-50) Accuracy 89.76% #78 of 83 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections