AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation

David Berthelot, Rebecca Roelofs, Kihyuk Sohn, Nicholas Carlini, Alexey Kurakin

ICLR 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use AdaMatch instead of FixMatch+DigitFive UDA · DigitFive UDAtarget accuracy: 95.6 -> 97.8Improved
Use AdaMatch instead of NoisyStudentDomainNet64 UDA · DomainNet64 UDAtarget accuracy: 21.4 -> 26.1Improved
Use AdaMatch instead of NoisyStudentDomainNet224 UDA · DomainNet224 UDAtarget accuracy: 23.9 -> 28.7Improved
Use ImageNet-pretrained AdaMatch rather than pretrained MCD after 8M imagesDomainNet224 UDA · DomainNet224 UDA, ImageNet pre-training, 8Mtarget accuracy: 22.3 -> 28.2Improved
Early-stop pretrained AdaMatch at 2M images rather than train for 8MAdaMatch · DomainNet224 UDA with ImageNet pre-trainingtarget accuracy: 28.2 -> 33.4Improved
Use AdaMatch instead of FixMatch+DomainNet224 SSL with 25 labels · DomainNet224 SSL, 25 labelstarget accuracy: 42.9 -> 46.4Improved
Use AdaMatch instead of FixMatch+DomainNet224 SSDA with 1 target label · DomainNet224 SSDA, 1 target labeltarget accuracy: 28.3 -> 34.8Improved
Use AdaMatch instead of FixMatch+DomainNet224 SSDA with 5 target labels · DomainNet224 SSDA, 5 target labelstarget accuracy: 38.7 -> 42.3Improved
Add random logit interpolation (ablation)AdaMatch · DomainNet64 UDA, 6 protocolsaccuracy: 25.2 -> 26.3Improved
Add distribution alignment (ablation)AdaMatch · DomainNet64 UDA, 6 protocolsaccuracy: 17.7 -> 26.3Improved
Add relative confidence thresholding (ablation)AdaMatch · DomainNet64 UDA, 6 protocolsaccuracy: 23.2 -> 26.3Improved
Increase unlabeled-to-labeled batch ratio (ablation)AdaMatch · DomainNet64 UDA, 6 protocolsaccuracyImproved

Later papers that compared with this method

4 later accepted papers report AdaMatch as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy