Papers › Exploring Localization for Self-supervised Fine-grained Contrastive Learning
Exploring Localization for Self-supervised Fine-grained Contrastive Learning
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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