AI Paper Atlas

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

Towards Effective Visual Representations for Partial-Label Learning

Shiyu Xia, Jiaqi Lv, Ning Xu, Gang Niu, Xin Geng

CVPR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 27 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
replace PiCO with PaPiPLL image classification · CIFAR-10, uniform partial labels q = 0.7accuracy: 2.50%Improved
replace PiCO with PaPiPLL image classification · SVHN, uniform partial labels q = 0.7accuracy: 0.96%Improved
replace the baseline PLL method with PaPiPLL image classification · CIFAR-100, instance-dependent partial labelsaccuracy: 4.57%Improved
replace the baseline PLL method with PaPiPLL image classification · CIFAR-10, instance-dependent partial labelsaccuracy: 4.40%Improved
add mixup augmentation (ablation)PaPi · CIFAR-100, q = 0.2accuracy: +1.47%Improved
add prototypical alignment loss (ablation)PaPi · CIFAR-100, q = 0.2accuracy: +7.19%Improved
use one strong and one weak augmentation rather than two weak augmentations (ablation)PaPi · CIFAR-100, q = 0.1accuracy: 81.65 \pm 0.27\% vs 79.35 \pm 0.14\%Improved
use one strong and one weak augmentation rather than two strong augmentations (ablation)PaPi · CIFAR-100, q = 0.1accuracy: 81.65 \pm 0.27\% vs 80.96 \pm 0.08\%Improved
use two strong augmentations rather than one strong and one weak (ablation)PaPi · CIFAR-10, q = 0.5accuracy: 96.90 \pm 0.09\% vs 96.91 \pm 0.05\%Mixed
remove contrastive learning and use guided prototypical alignmentPiCO · PLL image classificationaccuracyImproved

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