Research map / Detection and segmentation / Open-set and few-shot detection
Weakly Supervised Learning of Part Selection Model with Spatial Constraints for Fine-Grained Image Classification
Read the paperCheck 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 |
|---|---|---|---|
| add part selection with two spatial constraints | VGG-ft · CUB-200-2011 | accuracy: 74.91% →84.69% | Helped |
| add both box and parts constraints vs no constraints (ablation) | part selection · CUB-200-2011 | accuracy: 75.94 -> 84.69 | Helped |
| add parts constraint to box constraint (ablation) | part selection · CUB-200-2011 | accuracy: 81.01 -> 84.69 | Helped |
| add box constraint to parts constraint (ablation) | part selection · CUB-200-2011 | accuracy: 77.06 -> 84.69 | Helped |
| add co-segmentation after saliency extraction (ablation) | object localization · CUB-200-2011 | precision@IoU0.7: 19.31% -> 28.36% | Helped |
| use TSC instead of PD part detection | weakly supervised fine-grained classification · CUB-200-2011 | accuracy: 82.60 -> 84.69 | Helped |
Closest papers by meaning
- Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR 2020 · similarity 0.89)
- SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition (CVPR 2016 · similarity 0.89)
- Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up (CVPR 2019 · similarity 0.89)
- Part-Stacked CNN for Fine-Grained Visual Categorization (CVPR 2016 · similarity 0.88)
- Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement (CVPR 2025 · similarity 0.85)
- Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation (CVPR 2025 · similarity 0.85)
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.