Research map / Detection and segmentation / CNN features
Guided Semantic Flow
Sangryul Jeon, Dongbo Min, Seungryong Kim, Jihwan Choe, Kwanghoon Sohn
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 local geometry consistency loss Lgeo to pruning training (ablation) | Ours w/ResNet · SPair-71k | PCK@alpha_bb=0.1: 25.1 -> 28.5 | Improved |
| add silhouette consistency loss Lsil to pruning training (ablation) | Ours w/ResNet · SPair-71k | PCK@alpha_bb=0.1: 24.3 -> 28.5 | Improved |
| add first-stage pruning-network training before end-to-end training (ablation) | Ours w/ResNet · SPair-71k | PCK@alpha_bb=0.1: 30.2 -> 33.5 | Improved |
| replace ResNet-101 features with SFNet features | Ours · PF-PASCAL | PCK@alpha_img=0.1: 84.5 -> 87.8 | Improved |
| replace ResNet-101 features with SFNet features | Ours · SPair-71k | PCK@alpha_bb=0.1: 33.5 -> 36.1 | Improved |
| replace ResNet-101 features with SFNet features | Ours · Caltech-101 | LT-ACC: 0.88 -> 0.89 | 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.
- SFNet — SFNet: Learning Object-Aware Semantic Correspondence (CVPR 2019) · better on 3 of 3 shared results
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
- Proposal Flow: Semantic Correspondences from Object Proposals (TPAMI 2017 · similarity 0.91)
- Proposal Flow (CVPR 2016 · similarity 0.90)
- Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration (CVPR 2024 · similarity 0.90)
- DCTM: Discrete-Continuous Transformation Matching for Semantic Flow (ICCV 2017 · similarity 0.90)
- Deep Semantic Feature Matching (CVPR 2017 · similarity 0.90)
- SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching (CVPR 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.
