Research map / Detection and segmentation / Open-set and few-shot detection
Object-Aware Dense Semantic Correspondence
Fan Yang, Xin Li, Hong Cheng, Jianping Li, Leiting Chen
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 objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · FG3DCar | FAcc: 69.51 -> 87.46 | Improved |
| Add objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · FG3DCar | SAcc: 74.76 -> 85.58 | Improved |
| Add objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · JODS | FAcc: 55.10 -> 70.78 | Improved |
| Add objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · JODS | SAcc: 57.22 -> 68.44 | Improved |
| Add objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · PASCAL | FAcc: 61.62 -> 72.92 | Improved |
| Add objectness-driven SVM classifiers to the matching model (ablation) | Object-aware Hierarchical Graph · PASCAL | SAcc: 71.73 -> 78.21 | Improved |
| Use object-aware hierarchical matching with learned region classifiers | Dense semantic correspondence · FG3DCar | FAcc: 82.97 -> 87.46 | Improved |
| Use object-aware hierarchical matching with learned region classifiers | Dense semantic correspondence · JODS | FAcc: 64.40 -> 70.78 | Improved |
| Use object-aware hierarchical matching with learned region classifiers | Dense semantic correspondence · PASCAL | FAcc: 48.52 -> 72.92 | Improved |
| Use object-aware hierarchical matching with learned region classifiers | Dense semantic correspondence · Caltech-101 | LT-ACC: 0.79 -> 0.81 | Improved |
Closest papers by meaning
- Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration (CVPR 2024 · similarity 0.89)
- Deep Semantic Feature Matching (CVPR 2017 · similarity 0.88)
- Semantic Correspondence as an Optimal Transport Problem (CVPR 2020 · similarity 0.88)
- Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution (CVPR 2023 · similarity 0.87)
- SFNet: Learning Object-Aware Semantic Correspondence (CVPR 2019 · similarity 0.87)
- Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.86)
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.
