Research map / Detection and segmentation / CNN features
Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition
Xiao Liu, Jiang Wang, Shilei Wen, Errui Ding, Yuanqing Lin
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 |
|---|---|---|---|
| Use ground-truth bird bounding boxes during localization | Attribute-guided localizers · CUB-200-2011 | PCP (average): 66.2 -> 73.4 | Improved |
| Use localized attention regions rather than full-image input alone (ablation) | Attribute prediction · CUB-200-2011 | AUC (four-part average): 74.3 -> 73.7 | Hurt |
| Combine full-image and localized-attention predictions (ablation) | Attribute prediction · CUB-200-2011 | AUC (four-part average): 74.3 -> 76.6 | Improved |
| Add head and breast part features (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, without BB | Accuracy: 81.7% -> 84.7% | Improved |
| Add head and breast part features (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, with BB | Accuracy: 82.3% -> 84.9% | Improved |
| Add features from four localized parts (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, without BB | Accuracy: 81.7% -> 85.1% | Improved |
| Add features from four localized parts (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, with BB | Accuracy: 82.3% -> 85.3% | Improved |
| Add binary attribute labels (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, without BB | Accuracy: 81.7% -> 81.7% | No clear effect |
| Add binary attribute labels (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, with BB | Accuracy: 82.3% -> 82.2% | No clear effect |
| Add visual features from part attribute-prediction models (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, without BB | Accuracy: 81.7% -> 82.5% | Improved |
| Add visual features from part attribute-prediction models (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, with BB | Accuracy: 82.3% -> 82.9% | Improved |
| Combine four-part features with attribute-model features (ablation) | Full-image ResNet-50 classifier · CUB-200-2011, without BB | Accuracy | Improved |
Closest papers by meaning
- Interpretable and Accurate Fine-grained Recognition via Region Grouping (CVPR 2020 · similarity 0.86)
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection (NeurIPS 2025 · similarity 0.85)
- Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization (ICCV 2019 · similarity 0.85)
- Learning to Navigate for Fine-grained Classification (ECCV 2018 · similarity 0.84)
- Recurrent Attentional Reinforcement Learning for Multi-Label Image Recognition (AAAI 2018 · similarity 0.84)
- Navigating Real-World Partial Label Learning: Unveiling Fine-Grained Images with Attributes (AAAI 2024 · 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.
