Research map / Label-efficient and robust learning / Recognition and long-tail
PiCO: Contrastive Label Disambiguation for 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 representation learning and prototype-based label disambiguation | PLL classifier · CIFAR-10, q=0.5 | accuracy: 93.58 vs 87.78 | Improved |
| Add contrastive representation learning and prototype-based label disambiguation | PLL classifier · CIFAR-100, q=0.05 | accuracy: 72.74 vs 60.73 | Improved |
| Add clean-sample detection, semi-supervised contrastive learning, and mixup | PiCO · CIFAR-10, q=0.5, η=0.2 | accuracy: 80.07 -> 92.59 | Improved |
| Add clean-sample detection, semi-supervised contrastive learning, and mixup | PiCO · CIFAR-100, q=0.05, η=0.2 | accuracy: 59.81 -> 72.98 | Improved |
| Add prototype-based disambiguation instead of uniform pseudo targets (ablation) | PiCO · CIFAR-10, q=0.5 | accuracy: 84.50 -> 93.58 | Improved |
| Add contrastive loss alongside uniform pseudo targets (ablation) | PiCO · CIFAR-10, q=0.5 | accuracy: 76.46 -> 84.50 | Improved |
| Use moving-average prototype targets rather than direct soft prototype probabilities (ablation) | PiCO · CIFAR-10, q=0.5 | accuracy: 91.60 -> 93.58 | Improved |
| Use moving-average targets rather than direct one-hot nearest-prototype targets (ablation) | PiCO · CIFAR-100, q=0.05 | accuracy: 70.10 -> 72.74 | Improved |
| Add neighbor-augmented contrastive loss (ablation) | PiCO+ · CIFAR-10, q=0.5, η=0.2 | accuracy: 87.43 -> 92.59 | Improved |
| Add mixup training (ablation) | PiCO+ · CIFAR-100, q=0.05, η=0.2 | accuracy: 68.51 -> 72.98 | Improved |
| Add prototype-based label guessing loss for noisy samples (ablation) | PiCO+ · CIFAR-100, q=0.05, η=0.2 | accuracy: 71.98 -> 72.98 | Improved |
| Use distance-based clean-sample selection instead of small-loss selection (ablation) | PiCO+ · CIFAR-10, q=0.5, η=0.2 | accuracy: 91.22 -> 92.59 | Improved |
Later papers that compared with this method
22 later accepted papers report PiCO+ as a baseline in their results tables; 21 of them report a better number on most of the results they share with it.
- Neighbor-aware Label Refinement: Enhancing Unreliable Instance-Dependent Partial Labels (AAAI 2026 · better on 9 of 10 shared results)
- Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label Learning (ICML 2026 · better on 7 of 7 shared results)
- Evidential Deep Partial Label Learning to Quantify Disambiguation Uncertainty (CVPR 2026 · better on 5 of 7 shared results)
- Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning (ICLR 2026 · better on 3 of 3 shared results)
- Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning (ECCV 2026 · better on 2 of 2 shared results)
- Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning (CVPR 2026 · better on 1 of 1 shared result)
- IRNet: Iterative Refinement Network for Noisy Partial Label Learning (TPAMI 2025 · better on 9 of 9 shared results)
- Partial Label Causal Representation Learning for Instance-Dependent Supervision and Domain Generalization (AAAI 2025 · better on 0 of 2 shared results)
14 more not listed.
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 Robust Partial Label Learning (TPAMI 2023 · similarity 0.98)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.90)
- 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)
- Partial Label Causal Representation Learning for Instance-Dependent Supervision and Domain Generalization (AAAI 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.
