Research map / Detection and segmentation / Open-set and few-shot detection
Interpretable and Accurate Fine-grained Recognition via Region Grouping
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 region grouping, part-occurrence regularization, and attention-based classification | ResNet101 · iNaturalist 2017 | instance level accuracy: 61.1 -> 64.8 | Helped |
| Use fully convolutional testing | Ours · iNaturalist 2017 | instance level accuracy: 64.8 -> 66.8 | Helped |
| Use the proposed model instead of ResNet101 | ResNet101 · CUB-200-2011 | instance level accuracy: 87.7 -> 87.3 | Hurt |
| Use the proposed model instead of ResNet101 | ResNet101 · CelebA facial attribute recognition | average class accuracy: 91.5 -> 91.5 | No clear effect |
| Add part-occurrence regularization (ablation) | Ours · CelebA ablation split | localization error (%): 12.3 -> 8.4 | Helped |
| Add part-occurrence regularization (ablation) | Ours · CelebA ablation split | accuracy (%): 91.3 -> 91.5 | No clear effect |
| Add attention (ablation) | Ours · CelebA ablation split | accuracy (%): 91.5 -> 91.5 | No clear effect |
| Add attention (ablation) | Ours · CelebA ablation split | localization error (%): 7.6 -> 8.4 | Hurt |
Closest papers by meaning
- Part-Stacked CNN for Fine-Grained Visual Categorization (CVPR 2016 · similarity 0.92)
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery (NeurIPS 2026 · similarity 0.88)
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection (NeurIPS 2025 · similarity 0.87)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.87)
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.87)
- Recognize Any Regions (NeurIPS 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.