Papers › What Makes for Good Views for Contrastive Learning?
What Makes for Good Views for Contrastive Learning?
Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, Phillip Isola
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification (73% top-1 linear readout with a ResNet-50). In addition, transferring our models to PASCAL VOC object detection and COCO instance segmentation consistently outperforms supervised pre-training. Code:http://github.com/HobbitLong/PyContrast
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="2005.10243", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2005.10243")
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
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 |
|---|---|---|---|---|---|---|---|
| Contrastive Learning | imagenet-1k | ResNet50 | ImageNet Top-1 Accuracy | 73 | #2 of 14 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | InfoMin (ResNeXt-152) | Number of Params | 120M | #76 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | InfoMin (ResNeXt-152) | Top 1 Accuracy | 75.2% | #76 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | InfoMin (ResNet-50) | Number of Params | 24M | #92 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | InfoMin (ResNet-50) | Top 1 Accuracy | 73.0% | #92 of 144 | Archive leaderboard | report |
| Self-Supervised Image Classification | ImageNet | InfoMin (ResNet-50) | Top 5 Accuracy | 91.1% | #92 of 144 | 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.
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