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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace PiCO with PaPi | PLL image classification · CIFAR-10, uniform partial labels q = 0.7 | accuracy: 2.50% | Improved |
| replace PiCO with PaPi | PLL image classification · SVHN, uniform partial labels q = 0.7 | accuracy: 0.96% | Improved |
| replace the baseline PLL method with PaPi | PLL image classification · CIFAR-100, instance-dependent partial labels | accuracy: 4.57% | Improved |
| replace the baseline PLL method with PaPi | PLL image classification · CIFAR-10, instance-dependent partial labels | accuracy: 4.40% | Improved |
| add mixup augmentation (ablation) | PaPi · CIFAR-100, q = 0.2 | accuracy: +1.47% | Improved |
| add prototypical alignment loss (ablation) | PaPi · CIFAR-100, q = 0.2 | accuracy: +7.19% | Improved |
| use one strong and one weak augmentation rather than two weak augmentations (ablation) | PaPi · CIFAR-100, q = 0.1 | accuracy: 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 = 0.1 | accuracy: 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 = 0.5 | accuracy: 96.90 \pm 0.09\% vs 96.91 \pm 0.05\% | Mixed |
| remove contrastive learning and use guided prototypical alignment | PiCO · PLL image classification | accuracy | Improved |
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.
- PiCO — PiCO: Contrastive Label Disambiguation for Partial Label Learning (ICLR 2022) · better on 1 of 1 shared result
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
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · similarity 0.89)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.88)
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.87)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.87)
- Multi-Label Supervised Contrastive Learning (AAAI 2024 · similarity 0.87)
- Weakly-Supervised Contrastive Learning for Imprecise Class Labels (ICML 2025 · similarity 0.87)
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.
