AI Paper Atlas

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

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, Zsolt Kira

ECCV 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 118 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
add feature-based augmentation (AugF) with both consistency losses (ablation)image-based baseline · CIFAR-10, 250 labelserror rate (%): 19.55 -> 7.90Improved
add feature-based augmentation (AugF) with both consistency losses (ablation)image-based baseline · CIFAR-10, 4,000 labelserror rate (%): 6.08 -> 5.00Improved
add L_con-f (ablation)FeatMatch w/o L_con-f · CIFAR-10, 250 labelserror rate (%): 18.57 -> 7.90Improved
add L_con-f (ablation)FeatMatch w/o L_con-f · CIFAR-10, 4,000 labelserror rate (%): 6.09 -> 5.00Improved
add L_con-g (ablation)FeatMatch w/o L_con-g · CIFAR-10, 250 labelserror rate (%): 8.19 -> 7.90Improved
add L_con-g (ablation)FeatMatch w/o L_con-g · CIFAR-10, 4,000 labelserror rate (%): 5.16 -> 5.00Improved
use FeatMatch instead of PLCBPLCB · mini-ImageNet, 4,000 labelserror rate (%): 56.49 -> 39.05Improved
use FeatMatch instead of PLCBPLCB · CIFAR-100, 4,000 labelserror rate (%): 37.55 -> 31.06Improved
add feature-based augmentation under domain shiftsemi-supervised baseline · DomainNet, r_u=50%error rate (%): 65.82 -> 54.01Improved
add feature-based augmentation with clean unlabeled datasemi-supervised baseline · DomainNet, r_u=0%error rate (%): 56.63 -> 40.66Improved
increase share of shifted-domain unlabeled data from 0% to 50%FeatMatch · DomainNeterror rate (%): 40.66 -> 54.01Hurt
add distribution alignment and CutoutFeatMatch · CIFAR-10, 250 labelserror rate (%): 7.50 -> 6.00Improved

Later papers that compared with this method

1 later accepted paper reports FeatMatch as a baseline in their results tables; 1 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 0 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