Research map / Label-efficient and robust learning / Semi-supervised learning
CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision
Shuo Li, Yue He, Weiming Zhang, Wei Zhang, Xiao Tan, Junyu Han, Errui Ding, Jingdong Wang
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 coherent perturbation (image-level plus feature-level) to the baseline (ablation) | Cross pseudo supervision baseline · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 73.08 -> 73.44 | Improved |
| add adaptive contour guidance module (ACGM) (ablation) | CP baseline · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 73.44 -> 75.23 | Improved |
| add cross-fusion supervision (CFS) to CP baseline (ablation) | CP baseline · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 73.44 -> 75.22 | Improved |
| combine ACGM and CFS together on top of CP (ablation) | CFCG · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 73.08 -> 77.10 (single model) | Improved |
| use fusion inference with both learners instead of a single learner (ablation) | CFCG · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 77.10 -> 77.55 | Improved |
| train with CFS rather than average logits fusion of two learners (ablation) | CFCG single learner · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 76.01 -> 77.10 | Improved |
| learn contour weight gamma with an exponential schedule vs constant 0 (no weight map) (ablation) | ACGM · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 75.22 -> 77.10 | Improved |
| use log or constant-1 gamma schedule instead of exp (ablation) | ACGM · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 77.10 -> 75.56 (log); 75.95 (constant 1) | Hurt |
| use Gaussian kernel k=64 (img size/8) instead of 32 or 128 (ablation) | ACGM · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 75.86 (k=32), 75.88 (k=128) -> 77.10 | Improved |
| emphasize unreliable contour regions (contour-strengthened) instead of down-weighting them (ablation) | ACGM · PASCAL VOC 2012 1/8, ResNet-50 | mIoU: 75.01 -> 77.10 | Improved |
| use CFCG instead of CPS baseline | PASCAL VOC 2012 ResNet-50, all partitions · PASCAL VOC 2012 | mIoU: +2.00% to +3.43% w/o fusion; +2.50% to +3.88% w/ fusion | Improved |
Closest papers by meaning
- Semi-Supervised Semantic Segmentation With Cross-Consistency Training (CVPR 2020 · similarity 0.91)
- Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation (CVPR 2023 · similarity 0.90)
- Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision (CVPR 2021 · similarity 0.90)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.90)
- Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation (TPAMI 2023 · similarity 0.90)
- 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.
