Research map / Label-efficient and robust learning / Recognition and long-tail
Neighbor-aware Label Refinement: Enhancing Unreliable Instance-Dependent Partial Labels
Xijia Tang, Yuhua Qian, Chao Xu, Chenping Hou
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 |
|---|---|---|---|
| use NLAP neighbor-based label refinement instead of PRODEN | PRODEN · KMNIST (rn=0.3, rp=0.3) | test accuracy (OA, %): 84.69 -> 90.25 | Improved |
| use NLAP instead of PRODEN | PRODEN · FMNIST (rn=0.3, rp=0.5) | test accuracy (OA, %): 73.00 -> 79.90 | Improved |
| use NLAP instead of PRODEN | PRODEN · CIFAR-100 (rn=0.1, rp=0.1) | test accuracy (OA, %): 48.38 -> 51.50 | Improved |
| use NLAP instead of PRODEN | PRODEN · CIFAR-10 (rn=0.3, rp=0.3) | test accuracy (OA, %): 68.03 -> 70.61 | Improved |
| use NLAP instead of PiCO+ | PiCO+ · MNIST (rn=0.3, rp=0.5) | test accuracy (OA, %): 79.00 -> 78.41 | Hurt |
| use NLAP instead of PRODEN | PRODEN · CIFAR-100 (rn=0.3, rp=0.07) | test accuracy (OA, %): 39.38 -> 40.06 | No clear effect |
| vary neighbors K between 20 and 30 (ablation) | NLAP · KMNIST and CIFAR-100 | accuracy | No clear effect |
| increase initial threshold e0 (ablation) | NLAP · CIFAR-100 | accuracy | Improved |
| lengthen warm-up epochs (ablation) | NLAP · MNIST, CIFAR-10, CIFAR-100 | accuracy | No clear effect |
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 9 of 10 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
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.92)
- Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (AAAI 2024 · similarity 0.90)
- Partial Label Learning with a Partner (AAAI 2024 · similarity 0.89)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (NeurIPS 2025 · similarity 0.89)
- Disentangled 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.
