AI Paper Atlas

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

BidMatch: Boosting Semi-Supervised Learning by Bi-Dimensional Sample Weight Guidance

Xianling Yang, Zhiwen Yu, Sun Song, Kaixiang Yang

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 0 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 CIE to consistency regularization (ablation)consistency regularization · CIFAR-10 (40 labels)test error rate (%): 13.08 -> 8.69Improved
add CIE to consistency regularization (ablation)consistency regularization · CIFAR-100 (400 labels)test error rate (%): 51.56 -> 47.97Improved
add PPR to consistency regularization (ablation)consistency regularization · CIFAR-10 (40 labels)test error rate (%): 13.08 -> 4.91Improved
add PPR to consistency regularization (ablation)consistency regularization · CIFAR-100 (400 labels)test error rate (%): 51.56 -> 36.71Improved
add CIE to PPR (full BidMatch) (ablation)CR+PPR · CIFAR-10 (40 labels)test error rate (%): 4.91 -> 4.78Improved
add CIE to PPR (full BidMatch) (ablation)CR+PPR · CIFAR-100 (400 labels)test error rate (%): 36.71 -> 36.27Improved
use BidMatch instead of FixMatch with very few labelsFixMatch · CIFAR-10 (10 labels)test error rate (%): 24.79 -> 6.45Improved
use BidMatch instead of FixMatchFixMatch · STL-10 (40 labels)test error rate (%): 35.97 -> 13.75Improved
use BidMatch instead of SoftMatchSoftMatch · CIFAR-10 (10 labels)test error rate (%): 15.77 -> 6.45Improved
use BidMatch instead of SoftMatchSoftMatch · CIFAR-100 (10000 labels)test error rate (%): 22.03 -> 21.24Improved
use BidMatch instead of SoftMatchSoftMatch · SVHN (1000 labels)test error rate (%): 2.01 -> 2.01No clear effect
use BidMatch instead of FixMatchFixMatch · ImageNet (100k labels)top-1 error (%): 43.66 -> 40.04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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