AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning

Dong-Dong Wu, Zhaoyi Li, Xiang Li, Zhiqiang Shen

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 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 UMiP augmentationPRODEN · SVHN instance-dependent q1=1.0test accuracy: 83.74 -> 95.64Improved
add UMiP augmentationPRODEN · SVHN instance-dependent q1=0.6test accuracy: 91.79 -> 95.82Improved
add UMiP augmentationLWS · CUB-200 uniformtest accuracy: +4.57%, +6.53%, +10.2%Improved
add UMiP augmentationCRDPLL · SVHN instance-dependent q1=0.6test accuracy: 79.45 -> 79.70No clear effect
add UMiP augmentationPaPi · CIFAR-10 instance-dependent q1=1.0test accuracy: 52.25 -> 60.02Improved
add UMiP augmentationPRODEN · Lost real-worldtest accuracy: 71.15 -> 73.81Improved
use UMiP instead of PLDA augmentationLWS · Lost real-worldtest accuracy: 74.12 -> 76.28Improved
add UMiP augmentationinstance-dependent CIFAR-10 high ambiguity · local ambiguity degreeLAD: 0.993 -> 0.974Improved
add UMiP augmentationoriginal model · SVHN instance-dependentexpected calibration error: 11.01 -> 5.54Improved
add label renormalization step to UMiP (ablation)PRODEN, LWS, PiCO, ABLE, DIRK, PaPi · uniform PLL q3=0.9test accuracy: up to 8.85%Improved
add warm-up epochs before enabling UMiP (ablation)PRODEN · SVHN q1=0.8final accuracy: 95.82 -> 95.97No clear effect
change Beta parameter alpha away from 1.0 (0.5 or 2.0) (ablation)UMiP · SVHN q1=0.6test accuracyHurt

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