Research map / Vision-language and multimodal / Human and embodied modeling
Fine-Grained Image Classification via Combining Vision and Language
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 |
|---|---|---|---|
| combine the vision and language streams (ablation) | CVL · CUB-200-2011 | accuracy: 76.17% → 85.55% | Helped |
| add the language stream to the vision stream (ablation) | CVL · CUB-200-2011 | accuracy: 82.98% vs. 85.55% | Helped |
| add the vision stream to the language stream (ablation) | CVL · CUB-200-2011 | accuracy: 81.81% vs. 85.55% | Helped |
| fine-tune the language-stream image encoder (ablation) | Language stream · CUB-200-2011 | accuracy: 50.54 -> 77.80 | Helped |
| add object localization (ablation) | Language stream · CUB-200-2011 | accuracy: 77.80 -> 81.81 | Helped |
| fine-tune the image encoder (ablation) | DS-SJE · CUB-200-2011 zero-shot recognition | Top-1 accuracy: 54.0 -> 60.0 | Helped |
| add object localization (ablation) | DS-SJE · CUB-200-2011 zero-shot recognition | Top-1 accuracy: 60.0 -> 65.1 | Helped |
Closest papers by meaning
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.90)
- Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models (ICLR 2025 · similarity 0.88)
- Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation (ICLR 2026 · similarity 0.88)
- Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.87)
- Improving fine-grained understanding in image-text pre-training (ICML 2024 · similarity 0.87)
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection (NeurIPS 2025 · 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.