Research map / Label-efficient and robust learning / Semi-supervised learning
Collaborative Dual Representations for Semi-Supervised Partial Label Learning
Wei-Xuan Bao, Yong Rui, Min-Ling Zhang
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 pseudo-target smoothing (ablation) | CODUAL · CIFAR-10 (v=100, r=5) | accuracy: 32.88 -> 60.74 | Improved |
| add pseudo-target smoothing (ablation) | CODUAL · CIFAR-100 (v=100, r=10) | accuracy: 63.38 -> 72.85 | Improved |
| add pseudo-target smoothing (ablation) | CODUAL · CIFAR-100 (v=100, r=20) | accuracy: 54.34 -> 63.84 | Improved |
| add pseudo-target smoothing (ablation) | CODUAL · CIFAR-10 (v=400, r=5) | accuracy: 93.47 -> 94.54 | Improved |
| add graph reconstruction regularization (ablation) | CODUAL · CIFAR-100 (v=100, r=20) | accuracy: 49.71 -> 63.84 | Improved |
| add graph reconstruction regularization (ablation) | CODUAL · CIFAR-10 (v=400, r=5) | accuracy: 92.03 -> 94.54 | Improved |
| add graph reconstruction regularization (ablation) | CODUAL · CIFAR-10 (v=100, r=5) | accuracy: 40.71 -> 60.74 | Improved |
| add graph reconstruction regularization (ablation) | CODUAL · CIFAR-100 (v=100, r=10) | accuracy: 64.88 -> 72.85 | Improved |
| add both PS and GR (vs neither) (ablation) | CODUAL · CIFAR-100 (v=100, r=20) | accuracy: 49.84 -> 63.84 | Improved |
| CODUAL vs best baseline with fewer labels and more false positives | CODUAL · CIFAR-100 (v=50, r=20) | accuracy: 34.66 -> 43.61 | 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.
- FreeMatch+ — FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning (ICLR 2023) · 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
- Partial Label Learning with a Partner (AAAI 2024 · similarity 0.90)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.89)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.89)
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · similarity 0.89)
- 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 0.88)
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.
