Research map / Label-efficient and robust learning / Semi-supervised learning
GaussianMatch: Semi-Supervised Regression with Pseudo-Label Filtering via Multi-View Gaussian Consistency
Yin Wang, Hao Lu, Zixuan Wang, Zhen Qin, Li Kuang, Mengchu Zhou, Shuiguang Deng
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 GCF and AGDS pseudo-label filtering (ablation) | GaussianMatch · UTKFace (250 labels) | MAE: 7.41 -> 6.38 | Improved |
| add AGDS smoothing to GCF (ablation) | GaussianMatch · UTKFace (250 labels) | MAE: 6.85 -> 6.38 | Improved |
| use strong augmentation for the consistency branch (ablation) | GaussianMatch · UTKFace (250 labels) | MAE: 6.56 -> 6.38 | Improved |
| increase number of weak views K from 8 to 16 (ablation) | GaussianMatch · UTKFace (250 labels) | MAE: 6.38 -> 6.52 | Hurt |
| reduce number of weak views K from 8 to 2 (ablation) | GaussianMatch · UTKFace (250 labels) | MAE: 6.38 -> 6.74 | Hurt |
| use GaussianMatch instead of FixMatch-style classification pseudo-labeling | UTKFace age regression · UTKFace (250 labels) | MAE: 9.30 -> 6.38 | Improved |
| use GaussianMatch instead of RankUp under extreme label scarcity | UTKFace (30 labels) · UTKFace (30 labels) | MAE: 11.58 -> 9.80 | Improved |
| keep class-probability sharpening in MixMatch for regression | MixMatch · UTKFace (250 labels) | MAE: 9.42 -> 9.36 | No clear effect |
| use GaussianMatch instead of RankUp with 250 labels on UTKFace SRCC | UTKFace (250 labels) · UTKFace (250 labels) | SRCC: 0.835 -> 0.862 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- RankUp — RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier (NeurIPS 2024) · better on 9 of 9 shared results
- MixMatch — MixMatch: A Holistic Approach to Semi-Supervised Learning (NeurIPS 2019) · better on 3 of 3 shared results
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · 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
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels (NeurIPS 2025 · similarity 0.90)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.86)
- Leveraging Local Variance for Pseudo-Label Selection in Semi-supervised Learning (AAAI 2024 · similarity 0.86)
- Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL (ICML 2025 · similarity 0.86)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.86)
- Gradient Aligned Regression via Pairwise Losses (ICML 2025 · similarity 0.86)
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.
