Research map / Detection and segmentation / CNN features
Template Matching With Deformable Diversity Similarity
Itamar Talmi, Roey Mechrez, Lihi Zelnik-Manor
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 DDIS with deep features instead of BBS with deep features | Template matching · Template-matching benchmark, dFrame=25 | AUC: ≈ 11% | Improved |
| Use DDIS with deep features instead of BBS with deep features | Template matching · Template-matching benchmark, dFrame=50 | AUC: 15% | Improved |
| Use DDIS with deep features instead of BBS with deep features | Template matching · Template-matching benchmark, dFrame=100 | AUC: 8% | Improved |
| Use DDIS with color features instead of BBS with color features | Template matching · Template-matching benchmark, dFrame=25 | AUC: ≈ 10% | Improved |
| Use DDIS with color features instead of BBS with color features | Template matching · Template-matching benchmark, dFrame=50 | AUC: 16% | Improved |
| Use DDIS with color features instead of BBS with color features | Template matching · Template-matching benchmark, dFrame=100 | AUC: 21% | Improved |
| Replace BBS with DDIS using color features | Template matching · Template-matching benchmark | runtime: ~0.86s (0.59) vs 35.47s (80.36) | Improved |
Closest papers by meaning
- Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors (TPAMI 2017 · similarity 0.87)
- Efficient Sliding Window Computation for NN-Based Template Matching (ECCV 2018 · similarity 0.86)
- Matching Pixels Using Co-Occurrence Statistics (CVPR 2018 · similarity 0.85)
- HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods (NeurIPS 2024 · similarity 0.83)
- HomoMatcher: Achieving Dense Feature Matching with Semi-Dense Efficiency by Homography Estimation (AAAI 2025 · similarity 0.83)
- MATCHA: Towards Matching Anything (CVPR 2025 · similarity 0.83)
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.
