AI Paper Atlas

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

Towards Semi-supervised Learning with Non-random Missing Labels

Yue Duan, Zhen Zhao, Lei Qi, Luping Zhou, Lei Wang, Yinghuan Shi

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 25 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 class transition tracking Pseudo-Rectifying Guidance to FixMatchFixMatch · CIFAR-10 MNAR gamma=20accuracy: 56.26 -> 94.04Improved
add PRG to SimMatchSimMatch · CIFAR-100 MNAR gamma=50accuracy: 60.06 -> 65.65Improved
replace CADR with PRG on CIFAR-10 gamma=20FixMatch · CIFAR-10 MNAR gamma=20accuracy: 79.63 -> 94.04Improved
replace CADR with PRG on CIFAR-100FixMatch · CIFAR-100 MNAR gamma=50accuracy: 59.53 -> 59.11No clear effect
add PRG to FixMatch with only 40 labels and mild imbalanceFixMatch · CIFAR-10 (n_L=40, N_1=20)accuracy: 76.53 -> 77.44No clear effect
add class-distribution re-weighting of the transition matrix (ablation)PRG · CIFAR-10 MNAR gamma=20accuracy: 88.97 -> 94.04Improved
use multi-step transition H'^k with larger k instead of one step (ablation)PRG · CIFAR-10 MNAR gamma=20accuracy: 94.04 -> 82.60 (k=10)Hurt
use last-epoch class prediction to guide transitions (PRG Last) instead of current (ablation)PRG · CIFAR-10 MNAR gamma=20accuracy: 94.04 -> 93.81No clear effect
add PRG to FixMatch in mini-ImageNet MNARFixMatch · mini-ImageNet gamma=50accuracy: 23.56 -> 44.28Improved
add PRG to VIME on tabular MNISTVIME · Tabular MNISTaccuracy: 63.38 -> 59.41 (gamma=20); 64.80 -> 66.60 (gamma=100)Mixed
use too small tracked batch number N_B (ablation)PRG · CIFAR-10 MNAR gamma=20accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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