Papers › Jigsaw Clustering for Unsupervised Visual Representation Learning

Jigsaw Clustering for Unsupervised Visual Representation Learning

1 Apr 2021CVPR 2021 1arXiv:2104.00323archive 2025-07-28

Pengguang Chen, Shu Liu, Jiaya Jia

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded simultaneously and leading to additional computation. We propose a new jigsaw clustering pretext task in this paper, which only needs to forward each training batch itself, and reduces the training cost. Our method makes use of information from both intra- and inter-images, and outperforms previous single-batch based ones by a large margin. It is even comparable to the contrastive learning methods when only half of training batches are used. Our method indicates that multiple batches during training are not necessary, and opens the door for future research of single-batch unsupervised methods. Our models trained on ImageNet datasets achieve state-of-the-art results with linear classification, outperforming previous single-batch methods by 2.6%. Models transferred to COCO datasets outperform MoCo v2 by 0.4% with only half of the training batches. Our pretrained models outperform supervised ImageNet pretrained models on CIFAR-10 and CIFAR-100 datasets by 0.9% and 4.1% respectively. Code is available at https://github.com/Jia-Research-Lab/JigsawClustering

PaperPDFConference PDFCode

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

Code

Jia-Research-Lab/JigsawClustering officialmentioned in papermentioned on GitHubpytorch 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

ClusteringContrastive LearningRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationContrastive LearningDense ConnectionsFeedforward NetworkInfoNCEJigsawMoCoMoCo v2Random Gaussian Blur

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