Papers › Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning

Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning

21 Jan 2021CVPR 2021 1arXiv:2101.08482archive 2025-07-28

Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Zhuowen Tu, Stefano Soatto

We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. This design reduces the intrinsic cross-sample dependency of BN and enhances the generalization of the teacher. EMAN improves strong baselines for self-supervised learning by 4-6/1-2 points and semi-supervised learning by about 7/2 points, when 1%/10% supervised labels are available on ImageNet. These improvements are consistent across methods, network architectures, training duration, and datasets, demonstrating the general effectiveness of this technique. The code is available at https://github.com/amazon-research/exponential-moving-average-normalization.

PaperPDFConference PDFCode

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

Code

amazon-research/exponential-moving-average-normalization 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

Self-Supervised LearningSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification ImageNet - 0.2% labeled data FixMatch w/ EMAN (ResNet-50) ImageNet Top-1 Accuracy 43.6% #2 of 3 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data FixMatch-EMAN Top 1 Accuracy 63% #34 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data FixMatch-EMAN Top 1 Accuracy 74% #31 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.

Methods

Batch Normalization

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