Research map / Detection and segmentation / Weakly supervised detection and segmentation
CIAN: Cross-Image Affinity Net for Weakly 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 |
|---|---|---|---|
| Add cross-image affinity trained with cross-entropy loss (ablation) | CIAN with self-affinity baseline · Pascal VOC 2012 val | mIoU: 58.3 -> 59.1 | Helped |
| Add completion loss to cross-image representations (ablation) | CIAN with cross-entropy loss · Pascal VOC 2012 val | mIoU: 59.1 -> 62.5 | Helped |
| Add the retraining strategy (ablation) | CIAN with completion loss · Pascal VOC 2012 val | mIoU: 62.5 -> 64.3 | Helped |
| Use common-class instead of random-class image pairs (ablation) | CIAN with cross-entropy loss · Pascal VOC 2012 val | mIoU: 58.5 -> 59.1 | Helped |
| Use common-class instead of random-class image pairs (ablation) | CIAN with completion loss · Pascal VOC 2012 val | mIoU: 59.7 -> 62.5 | Helped |
| Add CIAN when 5% of training seeds are replaced with ground truth (ablation) | Segmentation baseline · Pascal VOC 2012 val, CRF, seed substitution 0.05 | mIoU: + 4.4 | Helped |
| Add CIAN when 10% of training seeds are replaced with ground truth (ablation) | Segmentation baseline · Pascal VOC 2012 val, CRF, seed substitution 0.10 | mIoU: + 5.1 | Helped |
Closest papers by meaning
- Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation (CVPR 2018 · similarity 0.92)
- Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers (CVPR 2022 · similarity 0.91)
- Bootstrapping the Performance of Webly Supervised Semantic Segmentation (CVPR 2018 · similarity 0.90)
- Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach (AAAI 2020 · similarity 0.90)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · 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.