Research map / Detection and segmentation / Open-set and few-shot detection
Proposal Flow
Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
Check 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 |
|---|---|---|---|
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with SS · Caltech-101 | LT-ACC: 0.68 -> 0.78 | Improved |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with SS · Caltech-101 | IoU: 0.48 -> 0.50 | Improved |
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with SS · Caltech-101 | LOC-ERR: 0.41 -> 0.25 | Improved |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with SS · PASCAL VOC classes | IoU: 0.39 -> 0.41 | Improved |
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with SS · PASCAL VOC classes | PCK: 0.13 -> 0.17 | Improved |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with SS · PASCAL VOC classes | PCK: 0.17 -> 0.17 | No clear effect |
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with EB · PF dataset | PCK (α = 0.1): 0.50 -> 0.44 | Hurt |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with EB · PF dataset | PCK (α = 0.1): 0.45 -> 0.44 | No clear effect |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with SS · PF dataset | PCK (α = 0.1): 0.55 -> 0.56 | Improved |
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with SS · PF dataset | PCK (α = 0.1): 0.52 -> 0.56 | Improved |
| Use local offset matching instead of probabilistic Hough matching (ablation) | Proposal flow with MCG · PF dataset | PCK (α = 0.1): 0.48 -> 0.49 | Improved |
| Use local offset matching instead of naive appearance matching (ablation) | Proposal flow with RP · PF dataset | PCK (α = 0.1): 0.53 -> 0.55 | Improved |
Closest papers by meaning
- Proposal Flow: Semantic Correspondences from Object Proposals (TPAMI 2017 · similarity 0.99)
- Guided Semantic Flow (ECCV 2020 · similarity 0.90)
- SFNet: Learning Object-Aware Semantic Correspondence (CVPR 2019 · similarity 0.89)
- Learning Semantic Correspondence Exploiting an Object-Level Prior (TPAMI 2020 · similarity 0.89)
- Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration (CVPR 2024 · similarity 0.88)
- Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos (ICLR 2024 · similarity 0.87)
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.
