Research map / Label-efficient and robust learning / Recognition and long-tail
Fine-Grained Retrieval Prompt Tuning
Shijie Wang, Jianlong Chang, Zhihui Wang, Haojie Li, Wanli Ouyang, Qi Tian
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 DPP with a frozen pre-trained model (ablation) | Pre-training (PT) · CUB-200-2011 | Recall@1: improves the Recall@1 accuracy by 10.8% | Improved |
| Use DPP with a frozen pre-trained model (ablation) | Pre-training (PT) · Stanford Cars | Recall@1: 15.8% | Improved |
| Add CAH to the frozen pre-trained model (ablation) | Pre-training (PT) · CUB-200-2011 | Recall@1: 16.7% | Improved |
| Add CAH to the frozen pre-trained model (ablation) | Pre-training (PT) · Stanford Cars | Recall@1: 18.0% | Improved |
| Combine DPP and CAH (ablation) | Frozen pre-trained model · CUB-200-2011 | Recall@1: 29.4% | Improved |
| Combine DPP and CAH (ablation) | Frozen pre-trained model · Stanford Cars | Recall@1: 32.2% | Improved |
| Add Instance Normalization within CAH (ablation) | DPP + PT + CAH without IN · CUB-200-2011 | Recall@1: 72.2% -> 74.3% | Improved |
| Add Instance Normalization within CAH (ablation) | DPP + PT + CAH without IN · Stanford Cars | Recall@1: 89.6% -> 91.1% | Improved |
| Use FRPT instead of full fine-tuning | ResNet-50 retrieval model · CUB-200-2011 | Recall@1: 4.6% | Improved |
| Use FRPT instead of full fine-tuning | ResNet-50 retrieval model · Stanford Cars | Recall@1: 6.7% | Improved |
| Use discriminative perturbation prompting instead of fixed CAM or bounding-box cropping (ablation) | CUB-200-2011 retrieval · CUB-200-2011 | Recall@1: 63.7% -> 74.3%; 67.6% -> 74.3% | Improved |
| Use FRPT instead of fine-tuning | ResNet-50 in the few-shot setting · CUB-200-2011 10-shot | Recall@1: 63.1% -> 66.6% | Improved |
Closest papers by meaning
- Fine-Grained Image Retrieval via Dual-Vision Adaptation (AAAI 2026 · similarity 0.91)
- Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator (CVPR 2023 · similarity 0.89)
- NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval (ICLR 2025 · similarity 0.86)
- Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval (NeurIPS 2026 · similarity 0.85)
- Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization (ICLR 2024 · similarity 0.85)
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection (NeurIPS 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.
