Research map / Detection and segmentation / Open-set and few-shot detection
Few-Shot Pattern Detection via Template Matching and Regression
Eunchan Jo, Dahyun Kang, Sanghyun Kim, Yunseon Choi, Minsu Cho
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 SAM decoder box refinement | TMR · RPINE | AP: 33.59 -> 29.66 | Hurt |
| add SAM decoder box refinement | TMR · RPINE-edgeless | AP: 33.25 -> 17.99 | Hurt |
| add SAM decoder box refinement | TMR · FSCD-147 | AP | Improved |
| add template matching feature to image feature (ablation) | TMR · RPINE | AP: 11.44 -> 33.59 | Improved |
| concatenate image feature F with template-matching feature (ablation) | TMR · RPINE | AP: 32.55 -> 33.59 | Improved |
| use channel-wise correlation instead of cosine similarity (ablation) | TMR · FSCD-147 | AP: 24.73 -> 36.01 | Improved |
| use 2D template matching instead of average-pooled prototype (ablation) | TMR · RPINE | AP: 20.94 -> 33.59 | Improved |
| use 2D template matching instead of average-pooled prototype (ablation) | TMR · FSCD-147 | AP: 28.91 -> 36.01 | Improved |
| condition box scale on exemplar size (ablation) | TMR · RPINE | AP: 23.88 -> 31.29 | Improved |
| condition box shift on exemplar size as well (ablation) | TMR · RPINE | AP: 31.29 -> 33.59 | Improved |
| regress box without exemplar size vs no regression (ablation) | TMR · RPINE | AP: 26.20 -> 23.88 | Hurt |
| upsample feature map from 64x64 to 128x128 (ablation) | TMR · RPINE | AP: 27.49 -> 33.59 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PseCo — PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection (ECCV 2022) · better on 2 of 2 shared results
- DAVE — DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting (CVPR 2024) · better on 1 of 1 shared result
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
- Few-Shot Object Counting and Detection (ECCV 2022 · similarity 0.89)
- A Low-Shot Object Counting Network With Iterative Prototype Adaptation (ICCV 2023 · similarity 0.88)
- Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment (AAAI 2022 · similarity 0.88)
- Single Domain Generalization for Few-Shot Counting via Universal Representation Matching (CVPR 2025 · similarity 0.86)
- Revisiting Few-Shot Object Detection with Vision-Language Models (NeurIPS 2024 · similarity 0.86)
- DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting (CVPR 2024 · similarity 0.86)
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.
