Research map / Detection and segmentation / Weakly supervised detection and segmentation
ACL-Net: Semi-supervised Polyp Segmentation via Affinity Contrastive Learning
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 |
|---|---|---|---|
| Use ACL-Net rather than U2PL | Semi-supervised polyp segmentation with ResNet-50 · Kvasir-SEG, 1/4 labeled | Dice (%): 84.47 -> 85.89 | Helped |
| Use ACL-Net rather than U2PL | Semi-supervised polyp segmentation with ResNet-50 · CVC-ClinicDB, 1/4 labeled | Dice (%): 83.27 -> 84.82 | Helped |
| Use ACL-Net rather than CAC | Semi-supervised polyp segmentation with ResNet-50 · CVC-300 | Dice (%): 85.18 -> 86.47 | Helped |
| Use ACL-Net rather than CAC | Semi-supervised polyp segmentation with ResNet-50 · ColonDB | Dice (%): 66.61 -> 68.71 | Helped |
| Use ACL-Net rather than CAC | Semi-supervised polyp segmentation with ResNet-50 · ETIS | Dice (%): 57.24 -> 58.89 | Helped |
| Add threshold refinement (ablation) | SupOnly · Kvasir-SEG, 1/4 labeled | Dice: 80.63 -> 81.29 | Helped |
| Add affinity contrast to threshold refinement (ablation) | Method I · Kvasir-SEG, 1/4 labeled | Dice: 81.29 -> 83.92 | Helped |
| Add affinity aggregation (ablation) | Method II · Kvasir-SEG, 1/4 labeled | Dice: 83.92 -> 84.47 | Helped |
| Add low-level affinity refinement (ablation) | Affinity contrast and threshold refinement · Kvasir-SEG, 1/4 labeled | Dice: 83.92 -> 84.86 | Helped |
| Add high-level affinity refinement (ablation) | Affinity contrast and threshold refinement · Kvasir-SEG, 1/4 labeled | Dice: 83.92 -> 85.26 | Helped |
| Add cross-image affinity aggregation and both low- and high-level affinity refinement (ablation) | ACL-Net · Kvasir-SEG, 1/4 labeled | Dice: 83.92 -> 85.89 | Helped |
Closest papers by meaning
- An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · similarity 0.87)
- Boost the Inference with Co-training: A Depth-guided Mutual Learning Framework for Semi-supervised Medical Polyp Segmentation (CVPR 2025 · similarity 0.87)
- Polyper: Boundary Sensitive Polyp Segmentation (AAAI 2024 · similarity 0.85)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.82)
- Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation (AAAI 2025 · similarity 0.82)
- ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement (AAAI 2025 · similarity 0.82)
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.