Papers › Debiasing, calibrating, and improving Semi-supervised Learning performance via simple...

Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projector

24 Oct 2023arXiv:2310.15764archive 2025-07-28

Khanh-Binh Nguyen

Recent studies on semi-supervised learning (SSL) have achieved great success. Despite their promising performance, current state-of-the-art methods tend toward increasingly complex designs at the cost of introducing more network components and additional training procedures. In this paper, we propose a simple method named Ensemble Projectors Aided for Semi-supervised Learning (EPASS), which focuses mainly on improving the learned embeddings to boost the performance of the existing contrastive joint-training semi-supervised learning frameworks. Unlike standard methods, where the learned embeddings from one projector are stored in memory banks to be used with contrastive learning, EPASS stores the ensemble embeddings from multiple projectors in memory banks. As a result, EPASS improves generalization, strengthens feature representation, and boosts performance. For instance, EPASS improves strong baselines for semi-supervised learning by 39.47\%/31.39\%/24.70\% top-1 error rate, while using only 100k/1\%/10\% of labeled data for SimMatch, and achieves 40.24\%/32.64\%/25.90\% top-1 error rate for CoMatch on the ImageNet dataset. These improvements are consistent across methods, network architectures, and datasets, proving the general effectiveness of the proposed methods. Code is available at https://github.com/beandkay/EPASS.

PaperPDFCode

Code

beandkay/epass officialmentioned 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 LearningSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification ImageNet - 1% labeled data SimMatch + EPASS (ResNet-50) Top 1 Accuracy 68.6% #24 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimMatch + EPASS (ResNet-50) Top 5 Accuracy 87.6 #24 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data CoMatch + EPASS (ResNet-50) Top 1 Accuracy 67.4% #25 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data CoMatch + EPASS (ResNet-50) Top 5 Accuracy 87.3 #25 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimMatch + EPASS (ResNet-50) Top 1 Accuracy 75.3% #27 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimMatch + EPASS (ResNet-50) Top 5 Accuracy 92.6 #27 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data CoMatch + EPASS (ResNet-50) Top 1 Accuracy 74.1% #30 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data CoMatch + EPASS (ResNet-50) Top 5 Accuracy 91.5 #30 of 75 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