Papers › DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision

DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision

11 May 2022arXiv:2205.05575archive 2025-07-28

Erik Wallin, Lennart Svensson, Fredrik Kahl, Lars Hammarstrand

Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, DoubleMatch, which combines the pseudo-labeling technique with a self-supervised loss, enabling the model to utilize all unlabeled data in the training process. We show that this method achieves state-of-the-art accuracies on multiple benchmark datasets while also reducing training times compared to existing SSL methods. Code is available at https://github.com/walline/doublematch.

PaperPDFCode

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):

Code

walline/doublematch officialmentioned in papertfSyntology: not harvested 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

Semi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification CIFAR-10, 250 Labels DoubleMatch Percentage error 5.56±0.42 #18 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 40 Labels DoubleMatch Percentage error 13.59±5.60 #19 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels DoubleMatch Percentage error 4.65±0.17 #20 of 49 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 2500 Labels DoubleMatch Percentage error 27.07± 0.26 #12 of 16 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels DoubleMatch Percentage error 41.83± 1.22 #14 of 21 Archive leaderboard report
Semi-Supervised Image Classification STL-10, 1000 Labels DoubleMatch Accuracy 95.65±0.20 #4 of 13 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels DoubleMatch Accuracy 97.90 ± 0.07 #2 of 17 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 250 Labels DoubleMatch Accuracy 97.63±0.35 #3 of 15 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 40 Labels DoubleMatch Percentage error 15.37±11.81 #5 of 5 Archive leaderboard report
Semi-Supervised Image Classification cifar-100, 10000 Labels DoubleMatch Percentage error 21.22± 0.17 #7 of 29 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