Research map / Label-efficient and robust learning / Semi-supervised learning
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao
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 |
|---|---|---|---|
| add contrastive loss (with uniform pseudo targets) (ablation) | PiCO · CIFAR-10 (q=0.5) | accuracy: 76.46 -> 84.50 | Improved |
| add prototype-based label disambiguation (ablation) | PiCO · CIFAR-10 (q=0.5) | accuracy: 84.50 -> 93.58 | Improved |
| add prototype-based label disambiguation (ablation) | PiCO · CIFAR-100 (q=0.05) | accuracy: 64.11 -> 72.74 | Improved |
| use hard prototype targets with moving average instead of soft prototype probabilities (ablation) | PiCO · CIFAR-10 (q=0.5) | accuracy: 81.67 -> 93.58 | Improved |
| add moving-average smoothing (phi>0) to one-hot prototype assignment (ablation) | PiCO · CIFAR-100 (q=0.05) | accuracy: 70.10 -> 72.74 | Improved |
| use distance-based clean selection instead of small-loss selection (ablation) | PiCO+ · Noisy PLL CIFAR-10 (q=0.5, eta=0.2) | accuracy: 91.22 -> 92.59 | Improved |
| add semi-supervised training on noisy samples beyond clean-only PiCO (ablation) | PiCO+ · Noisy PLL CIFAR-10 (q=0.5, eta=0.2) | accuracy: 87.63 -> 92.59 | Improved |
| add prototype-based label guessing loss L_n-cls (ablation) | PiCO+ · Noisy PLL CIFAR-10 (q=0.5, eta=0.2) | accuracy: 91.14 -> 92.59 | Improved |
| add label-driven noisy contrastive loss L_n-cont (ablation) | PiCO+ · Noisy PLL CIFAR-10 (q=0.5, eta=0.2) | accuracy: 90.87 -> 92.59 | Improved |
| add kNN neighbor-augmented contrastive loss (ablation) | PiCO+ · Noisy PLL CIFAR-10 (q=0.5, eta=0.2) | accuracy: 87.43 -> 92.59 | Improved |
| add mixup training (ablation) | PiCO+ · Noisy PLL CIFAR-100 (q=0.05, eta=0.2) | accuracy: 68.51 -> 72.98 | Improved |
| raise prototype momentum gamma from 0.99 to 0.999 (ablation) | PiCO · CIFAR-100 (q=0.05) | accuracy: 72.74 -> 67.33 | Hurt |
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 4 of 4 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
- PiCO: Contrastive Label Disambiguation for Partial Label Learning (ICLR 2022 · similarity 0.98)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.91)
- Towards Effective Visual Representations for Partial-Label Learning (CVPR 2023 · similarity 0.89)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.89)
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · similarity 0.88)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.88)
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.
