Papers › What Makes for Good Views for Contrastive Learning?

What Makes for Good Views for Contrastive Learning?

20 May 2020NeurIPS 2020 12arXiv:2005.10243archive 2025-07-28

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

PaperPDFConference PDFCode

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

Code

HobbitLong/PyContrast mentioned 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 LearningData AugmentationGeneral ClassificationInstance SegmentationObject DetectionRepresentation LearningSelf-Supervised Image ClassificationSemantic SegmentationUnsupervised Pre-trainingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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