Research map / Label-efficient and robust learning / Semi-supervised learning
Enhanced Soft Label for Semi-Supervised Semantic Segmentation
Jie Ma, Chuan Wang, Yang Liu, Liang Lin, Guanbin Li
This paper tried a common change: Add a contrastive loss
add pixel-to-part contrastive loss on top of DSL · Pascal VOC classic Full (1464) · mIoU: 80.41 -> 81.77 Improved
What 1,317 accepted papers report for this change
- 1,253 improved
- 22 no clear effect
- 16 mixed
- 26 hurt
- Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering ICML 2026 · add contrastive learning · SearchSnippets · ACC: 56.65 -> 80.12Improved
- SleepLM: Natural-Language Intelligence for Human Sleep ICML 2026 · add contrastive objective to captioning (CoCa vs Cap) · sleep event IoU · IoU: 29.2 -> 27.4Hurt
- LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations ICML 2026 · add contrastive loss L_con · FS1000 average · Spearman correlation: 0.759 -> 0.789Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 hard pseudo labels for unlabeled images (ablation) | supervised baseline · Pascal VOC classic Full (1464) | mIoU: 72.50 -> 78.32 | Improved |
| replace hard label with dynamic soft label (ablation) | ESL · Pascal VOC classic Full (1464) | mIoU: 78.32 -> 80.41 | Improved |
| add pixel-to-part contrastive loss on top of DSL (ablation) | ESL · Pascal VOC classic Full (1464) | mIoU: 80.41 -> 81.77 | Improved |
| add pixel-to-part contrastive loss to hard label alone (ablation) | hard-label self-training · Pascal VOC classic Full (1464) | mIoU: 78.32 -> 80.26 | Improved |
| use small eta (0.80) so DSL degrades to hard label (ablation) | DSL · Pascal VOC classic Full (1464) | mIoU: 80.41 -> 78.43 | Hurt |
| use fixed top-5 dominant classes instead of dynamic accumulated-probability threshold (ablation) | DSL · Pascal VOC classic Full (1464) | mIoU: 80.41 -> 79.89 | Hurt |
| raise eta from 0.95 to 0.99 (ablation) | DSL · Pascal VOC classic Full (1464) | mIoU: 80.41 -> 80.28 | No clear effect |
| use K=3 subclass prototypes instead of K=1 (pixel-to-region) (ablation) | pixel-to-part contrast · Pascal VOC classic Full (1464) | mIoU: 80.74 -> 81.39 | Improved |
| increase subclass number K beyond 5 (ablation) | pixel-to-part contrast · Pascal VOC classic Full (1464) | mIoU: 81.77 -> 81.72 (K=7); 81.64 (K=10) | No clear effect |
| dynamic soft label vs hard label with fewer labels (ablation) | ESL · Pascal VOC classic 1/16 (92) | mIoU: +5.53 (92 labels) vs +2.09 (1464 labels) | Improved |
| use more labeled data of mixed quality (blender 5291 vs classic 1464) | ESL · Pascal VOC | mIoU: 81.77 -> 79.98 | Hurt |
Closest papers by meaning
- Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant (NeurIPS 2022 · similarity 0.90)
- PseudoSeg: Designing Pseudo Labels for Semantic Segmentation (ICLR 2021 · similarity 0.89)
- Re-Distributing Biased Pseudo Labels for Semi-Supervised Semantic Segmentation: A Baseline Investigation (ICCV 2021 · similarity 0.89)
- ST++: Make Self-Training Work Better for Semi-Supervised Semantic Segmentation (CVPR 2022 · similarity 0.89)
- Learning from Future: A Novel Self-Training Framework for Semantic Segmentation (NeurIPS 2022 · similarity 0.89)
- Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective (NeurIPS 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.
