Research map / Label-efficient and robust learning / Semi-supervised learning
Graph-BAS3Net: Boundary-Aware Semi-Supervised Segmentation Network With Bilateral Graph Convolution
Huimin Huang, Lanfen Lin, Yue Zhang, Yingying Xu, Jing Zheng, XiongWei Mao, Xiaohan Qian, Zhiyi Peng, Jianying Zhou, Yen-Wei Chen, Ruofeng Tong
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 boundary detection network (ablation) | GN_s · LiTS 10% labeled | Dice (%): 83.87 -> 86.43 | Improved |
| feed boundary result to discriminator (ablation) | BAS3Net · LiTS 10% labeled | Dice (%): 89.56 -> 91.11 | Improved |
| add semantic graph with segmentation attention map (Gs) (ablation) | BAS3Net · LiTS 10% labeled | Dice (%): 91.11 -> 92.56 | Improved |
| add boundary graph with edge attention map (Gb) (ablation) | BAS3Net · LiTS 10% labeled | Dice (%): 91.11 -> 91.82 | Improved |
| add bilateral (inter-task) graph reasoning (ablation) | BAS3Net + BGCM · LiTS 10% labeled | Dice (%): 91.82 -> 93.19 | Improved |
| add self-taught semi-supervised loss on unlabeled data (ablation) | Graph-BAS3Net · LiTS 10% labeled | Dice (%): 89.54 -> 92.99 | Improved |
| raise confidence threshold T_semi from 0.3 to 1.0 (ablation) | Graph-BAS3Net · LiTS 10% labeled | Dice (%): 93.19 -> 91.81 | Hurt |
| increase boundary loss weight lambda_det from 0 to 1.0 (ablation) | Graph-BAS3Net · LiTS 100% labeled | Dice (%): 93.54 -> 94.73 | Improved |
| add adversarial loss weight lambda_adv 0.005 (ablation) | Graph-BAS3Net · LiTS 100% labeled | Dice (%): 94.73 -> 95.58 | Improved |
| increase lambda_adv from 0.005 to 0.05 (ablation) | Graph-BAS3Net · LiTS 100% labeled | Dice (%): 95.58 -> 95.03 | Hurt |
| replace Graph-BAS3Net by BAS3Net (remove BGCM) (ablation) | Graph-BAS3Net · LiTS 10% labeled | Dice (%): 91.11 -> 93.19 | Improved |
| add BGCM, gain at full labels | BAS3Net · LiTS 100% labeled | Dice (%): 95.23 -> 95.58 | Improved |
Closest papers by meaning
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.87)
- GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation (ICML 2025 · similarity 0.87)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 2025 · similarity 0.85)
- Boost the Inference with Co-training: A Depth-guided Mutual Learning Framework for Semi-supervised Medical Polyp Segmentation (CVPR 2025 · similarity 0.85)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.85)
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.
