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 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

amazon-research/exponential-moving-average-normalization officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Momentum Contrast for Unsupervised Visual Representation Learning (arXiv:1911.05722; that paper's own run record: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified), FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (arXiv:2001.07685; that paper's own run record: 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 unverified) and Bootstrap your own latent: A new approach to self-supervised Learning (arXiv:2006.07733; that paper's own run record: 62 ran (of which 19 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 1 violated, 37 with no contract checked; 20 where Syntology's instrument failed) · 17 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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