Research map / Detection and segmentation / CNN features
SCNet: Learning Semantic Correspondence
Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce
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 geometric consistency term (AG) to appearance-only SCNet (ablation) | SCNet-A · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | mean PCK@0.1: 66.3 -> 69.7 | Improved |
| add the AG+ geometric variant over AG (ablation) | SCNet-AG · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | mean PCK@0.1: 69.7 -> 72.2 | Improved |
| fine-tune all VGG16 layers instead of only FC layers (ablation) | SCNet · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | PCK | No clear effect |
| add geometry (AG) on transfer to PF-WILLOW (ablation) | SCNet-A · PF-WILLOW (trained on PF-PASCAL) | PCK@0.1: 0.725 -> 0.721 | No clear effect |
| add AG+ geometry on transfer to PF-WILLOW (ablation) | SCNet-A · PF-WILLOW (trained on PF-PASCAL) | PCK@0.1: 0.725 -> 0.704 | Hurt |
| replace HOG with SCNet-A learned features in LOM matching (ablation) | LOM · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | matching performance | Improved |
| retrain UCN on PF-PASCAL instead of raw network (ablation) | UCN · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | mean PCK@0.1: 36.0 -> 55.6 | Improved |
| use SCNet-AG+ instead of LOM with SCNet features for speed | SCNet-AG+ · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | runtime: 3.15 s -> 0.33 s | Improved |
| use RP proposals instead of uniform sampling (ablation) | SCNet-AG+ · PF-PASCAL (mean PCK@0.1, 1000 RP proposals) | PCR/mIoU | Improved |
| use learned SCNet-AG+ instead of FCSS w/PF on PASCAL Parts | SCNet-AG+ · PASCAL Parts | PCK@0.05: 0.29 -> 0.18 | Hurt |
| use SCNet-AG+ instead of LOM HOG | SCNet-AG+ · PASCAL Parts | IoU: 0.41 -> 0.48 | Improved |
Closest papers by meaning
- SFNet: Learning Object-Aware Semantic Correspondence (CVPR 2019 · similarity 0.92)
- Learning Semantic Correspondence Exploiting an Object-Level Prior (TPAMI 2020 · similarity 0.92)
- Semantic Correspondence: Unified Benchmarking and a Strong Baseline (TPAMI 2025 · similarity 0.90)
- Universal Correspondence Network (NeurIPS 2016 · similarity 0.90)
- Pyramidal Semantic Correspondence Networks (TPAMI 2021 · similarity 0.88)
- Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration (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.
