Research map / Detection and segmentation / Weakly supervised detection and segmentation
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-Segmentation
Yunchun Chen, Yen‐Yu Lin, Ming–Hsuan Yang, Jia‐Bin Huang
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 object co-segmentation stream to matching network (ablation) | joint model · TSS (semantic matching) | avg PCK: 0.751 -> 0.769 | Improved |
| add semantic matching stream to co-segmentation network (ablation) | joint model · TSS (object co-segmentation) | avg Jaccard index: 0.73 -> 0.84 | Improved |
| add semantic matching stream to co-segmentation network (ablation) | joint model · TSS (object co-segmentation) | avg precision: 0.899 -> 0.947 | Improved |
| add perceptual contrastive loss (ablation) | co-segmentation · Internet | avg Jaccard index: 0.38 -> 0.70 | Improved |
| add perceptual contrastive loss (ablation) | co-segmentation · Internet | avg precision: 0.425 -> 0.935 | Improved |
| add cross-network consistency loss (ablation) | co-segmentation · Internet | avg Jaccard index: 0.68 -> 0.70 | Improved |
| add cross-network consistency loss (ablation) | semantic matching · PF-WILLOW | PCK alpha=0.05: 0.514 -> 0.538 | Improved |
| add foreground-guided matching loss (ablation) | semantic matching · PF-WILLOW | PCK alpha=0.05: 0.494 -> 0.538 | Improved |
| add perceptual contrastive loss (ablation) | semantic matching · PF-WILLOW | PCK alpha=0.05: 0.502 -> 0.538 | Improved |
| add forward-backward consistency loss (ablation) | semantic matching · PF-WILLOW | PCK alpha=0.05: 0.529 -> 0.538 | Improved |
| add transitivity consistency loss (ablation) | semantic matching · PF-WILLOW | PCK alpha=0.05: 0.532 -> 0.538 | Improved |
| add foreground-guided matching loss (ablation) | co-segmentation · Internet | avg precision: 0.918 -> 0.935 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PARN — PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation (ECCV 2020 · similarity 0.90)
- Looking Beyond Single Images for Weakly Supervised Semantic Segmentation Learning (TPAMI 2022 · similarity 0.90)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers (CVPR 2022 · similarity 0.89)
- Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation (CVPR 2018 · similarity 0.89)
- Deep Semantic Feature Matching (CVPR 2017 · 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.
