Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
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 |
|---|---|---|---|
| add prototype-based predictor with consistency loss (ablation) | Ours · VOC classic 1/16, Cutout augmentation | mIoU: 66.86 -> 69.24 | Helped |
| add prototype-based predictor with consistency loss (ablation) | Ours · VOC classic 1/16, ClassMix augmentation | mIoU: 66.93 -> 69.36 | Helped |
| add prototype-based predictor (ablation) | Ours · VOC classic 1/16 feature analysis | intra-class variance trace: 168.92 -> 127.63 | Helped |
| add prototype-based predictor (ablation) | Ours · VOC classic 1/16 feature analysis | inter/intra variance ratio: 0.45 -> 2.22 | Helped |
| add prototype update during training (ablation) | Ours · PASCAL VOC 2012 classic | mIoU | Helped |
| use prototype-based predictor only (no linear predictor) (ablation) | Ours · PASCAL VOC 2012 classic | mIoU | Hurt |
| raise confidence threshold from 0.70 to 0.95 (ablation) | Ours · VOC classic 1/16 | mIoU (linear classifier): 64.89 -> 71.01 | Helped |
| prototype consistency method vs U2PL | ResNet-101 DeepLabv3+ · PASCAL VOC 2012 classic 1/8 | mIoU: 69.15 -> 74.71 | Helped |
| prototype consistency method vs AEL | ResNet-101 DeepLabv3+ · Cityscapes 1/16 | mIoU: 74.45 -> 73.41 | Hurt |
Closest papers by meaning
- Semi-Supervised Semantic Segmentation via Derivative Label Propagation (AAAI 2026 · similarity 0.93)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.90)
- AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- ScaleMatch: Multi-scale Consistency Enhancement for Semi-supervised Semantic Segmentation (AAAI 2025 · similarity 0.89)
- CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.89)
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.