Research map / Vision-language and multimodal / Multimodal LLMs
Benchmarking Vision-Language Models for Microscopic Plant Image Understanding
Tianqi Wei, Xin Yu, Zhi Chen, Scott C Chapman, Zi Helen 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 three-step chain-of-thought prompting (ablation) | Gemini 2.5-Pro · PlantMicro identification | macro accuracy: 62.93 -> 61.28 | Hurt |
| add three-step chain-of-thought prompting (ablation) | QwenVLM-7B · PlantMicro identification | macro accuracy: 51.98 -> 57.99 | Improved |
| add 1-shot in-context example (ablation) | GPT-5 · PlantMicro localization | mAP@0.5: 56.66 -> 53.73 | Hurt |
| add 1-shot in-context example (ablation) | QwenVLM-7B · PlantMicro localization | mAP@0.5: 65.05 -> 62.79 | Hurt |
| add 1-shot in-context example (ablation) | QwenVLM-7B · PlantMicro counting | MAE: 3.38 -> 3.11 | Improved |
| add 1-shot in-context example (ablation) | GPT-5 · PlantMicro counting | MAE: 2.07 -> 2.28 | Hurt |
| add retrieval-augmented most-similar demonstration (ablation) | QwenVLM-7B · PlantMicro identification | macro accuracy: 51.98 -> 68.63 | Improved |
| add retrieval-augmented demonstration (ablation) | LLaVA-13B · PlantMicro identification | macro accuracy: 37.24 -> 57.75 | Improved |
| add retrieval-augmented demonstration (ablation) | LLaVA-Next-13B · PlantMicro identification | macro accuracy: 41.20 -> 58.18 | Improved |
| closed-source vs open-source VLMs | VLMs · PlantMicro identification | macro accuracy: 51.98 (QwenVLM-7B) -> 63.08 (Gemini 2.5-Flash) | Improved |
| closed-source vs open-source on localization | VLMs · PlantMicro localization | mAP@0.5: GPT-5 56.66 vs QwenVLM-7B 65.05 | Hurt |
Closest papers by meaning
- Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding (NeurIPS 2024 · similarity 0.89)
- Utilizing Vision-Language Models for Detection of Leaf-Based Diseases in Tomatoes (AAAI 2025 · similarity 0.88)
- BioCLIP: A Vision Foundation Model for the Tree of Life (CVPR 2024 · similarity 0.87)
- VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images (NeurIPS 2024 · similarity 0.87)
- AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark (NeurIPS 2025 · similarity 0.86)
- MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research (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.
