Research map / Image generation / Autoregressive and latent generation
QATM: Quality-Aware Template Matching for Deep Learning
Jiaxin Cheng, Yue Wu, Wael AbdAlmageed, Premkumar Natarajan
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 |
|---|---|---|---|
| Replace BUPM matching with QATM (ablation) | BUPM network · Shibuya | ROC-AUC: 0.764 -> 0.777 | Improved |
| Replace BUPM matching with QATM (ablation) | BUPM network · Shibuya | Average precision: 0.781 -> 0.801 | Improved |
| Replace BUPM matching with QATM (ablation) | BUPM network · Wikimedia Common | ROC-AUC: 0.864 -> 0.857 | Hurt |
| Replace BUPM matching with QATM (ablation) | BUPM network · Wikimedia Common | Average precision: 0.886 -> 0.886 | No clear effect |
| Replace BUPM matching with QATM (ablation) | BUPM network · Wikimedia Common | F1: 0.33 -> 0.40 | Improved |
| Replace BUPM matching with QATM (ablation) | BUPM network · Wikimedia Common | IoU: 0.24 -> 0.29 | Improved |
| Replace GeoCNN matching scores with QATM scores (ablation) | GeoCNN · PF-PASCAL | PCK (average): 71.9 -> 75.9 | Improved |
| Use QATM rather than raw matching scores | template matching on OTB · OTB | AUC: roughly 2% | Improved |
| Use QATM rather than competing template matching methods | template matching on MOTB · MOTB | AUC: roughly 9% | Improved |
Closest papers by meaning
- Deep Matching Prior: Test-Time Optimization for Dense Correspondence (ICCV 2021 · similarity 0.85)
- OATM: Occlusion Aware Template Matching by Consensus Set Maximization (CVPR 2018 · similarity 0.85)
- XFeat: Accelerated Features for Lightweight Image Matching (CVPR 2024 · similarity 0.83)
- GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers (NeurIPS 2025 · similarity 0.82)
- GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 · similarity 0.82)
- ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses (NeurIPS 2024 · similarity 0.81)
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.
