Research map / Label-efficient and robust learning / Semi-supervised learning
Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply iMAS instead of PSMT | Semi-supervised segmentation on PASCAL VOC 2012 classic val · 1/8 (183 labeled images) | mIOU: 71.0 -> 75.3 | Helped |
| Apply iMAS instead of CPS | Semi-supervised segmentation on Cityscapes val · 1/16 (186 labeled images) | mIOU: 74.4 -> 75.2 | Helped |
| Add instance-specific weighting to the unsupervised loss (ablation) | iMAS on PASCAL VOC 2012 val · 1/8 (1323 labeled images) | mIOU: 72.1 -> 75.5 | Helped |
| Add model-adaptive intensity augmentation (ablation) | iMAS on PASCAL VOC 2012 val · 1/8 (1323 labeled images) | mIOU: 72.1 -> 76.5 | Helped |
| Add model-adaptive CutMix augmentation (ablation) | iMAS on PASCAL VOC 2012 val · 1/8 (1323 labeled images) | mIOU: 72.1 -> 76.9 | Helped |
| Combine adaptive loss weighting, intensity augmentation, and CutMix augmentation (ablation) | iMAS on PASCAL VOC 2012 val · 1/8 (1323 labeled images) | mIOU: 72.1 -> 77.9 | Helped |
Closest papers by meaning
- Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation (CVPR 2023 · similarity 0.91)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.89)
- WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels (CVPR 2025 · similarity 0.89)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.88)
- RWMS: Reliable Weighted Multi-Phase for Semi-supervised Segmentation (AAAI 2024 · similarity 0.88)
- ScaleMatch: Multi-scale Consistency Enhancement for Semi-supervised Semantic Segmentation (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.