Research map / Vision-language and multimodal / Human and embodied modeling
Language-driven Fine-grained Retrieval
Shijie Wang, Xin Yu, Yadan Luo, Zijian Wang, Pengfei Zhang, Zi Huang
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 EMA-updated projectors for alignment loss instead of backprop-trained projectors (ablation) | LaFG with Laux · CUB-200-2011 | Recall@1: 85.3% -> 87.2% | Improved |
| add language-driven alignment loss to Laux (ablation) | LaFG · CUB-200-2011 | Recall@1: 82.6% -> 87.2% | Improved |
| use LLM-generated attribute descriptions instead of hand-crafted template (ablation) | LaFG · CUB-200-2011 | Recall@1: 83.7% -> 85.3% | Improved |
| add clustered attribute vocabulary and category-specific attribute selection (ablation) | LaFG with LLM descriptions · CUB-200-2011 | Recall@1: 85.3% -> 87.2% | Improved |
| increase LLM descriptions per class from 20 to 25 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 86.3% | Hurt |
| increase LLM descriptions per class from 5 to 20 (ablation) | LaFG · CUB-200-2011 | Recall@1: 81.4% -> 87.2% | Improved |
| increase vocabulary size from 128 to 512 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 85.9% | Hurt |
| reduce vocabulary size from 128 to 32 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 84.3% | Hurt |
| increase Top-K attributes from 40 to 48 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 86.9% | Hurt |
| increase projector distribution dimension from 256 to 512 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 86.9% | Hurt |
| vary EMA update ratio alpha from 0.2 to 0.1 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 87.1% | No clear effect |
| increase EMA update ratio to 0.6 or 0.8 (ablation) | LaFG · CUB-200-2011 | Recall@1: 87.2% -> 86.6% | Hurt |
Closest papers by meaning
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.89)
- Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval (NeurIPS 2023 · similarity 0.89)
- Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models (ICLR 2025 · similarity 0.89)
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection (NeurIPS 2025 · similarity 0.89)
- FLAIR: VLM with Fine-grained Language-informed Image Representations (CVPR 2025 · similarity 0.88)
- Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval (NeurIPS 2026 · similarity 0.87)
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.
