Research map / Vision-language and multimodal / Multimodal LLMs
A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis
Xiang Liu, Zhaoxiang Liu, Huan Hu, Zezhou Chen, Kohou Wang, Kai Wang, Shiguo Lian
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 |
|---|---|---|---|
| finetune on the CDDM dataset | Qwen-VL-Chat-7B · CDDM test, disease classification | accuracy: 5.0% -> 91.5% | Improved |
| finetune on the CDDM dataset | LLaVA-v1.5-7B · CDDM test, disease classification | accuracy: 5.9% -> 91.8% | Improved |
| unfreeze the visual encoder (LoRA on encoder) during finetuning (ablation) | Qwen-VL-Chat-7B · CDDM test, disease classification | accuracy: 66.1% -> 91.5% | Improved |
| unfreeze the visual encoder (LoRA on encoder) during finetuning (ablation) | LLaVA-v1.5-7B · CDDM test, disease classification | accuracy: 82.1% -> 91.8% | Improved |
| unfreeze the visual encoder (LoRA on encoder) during finetuning (ablation) | Qwen-VL-Chat-7B · CDDM test, crop classification | accuracy: 84.4% -> 97.4% | Improved |
| unfreeze the visual encoder (LoRA on encoder) during finetuning (ablation) | Qwen-VL-Chat-7B · Crop disease knowledge QA | normalized GPT-4 score: 88.5 -> 84 | Hurt |
| unfreeze the visual encoder (LoRA on encoder) during finetuning (ablation) | LLaVA-v1.5-7B · Crop disease knowledge QA | normalized GPT-4 score: 98 -> 96.5 | Hurt |
Closest papers by meaning
- AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark (NeurIPS 2025 · similarity 0.93)
- AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning (NeurIPS 2026 · similarity 0.91)
- MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations (NeurIPS 2025 · similarity 0.89)
- Empowering and Assessing the Utility of Large Language Models in Crop Science (NeurIPS 2024 · similarity 0.88)
- Utilizing Vision-Language Models for Detection of Leaf-Based Diseases in Tomatoes (AAAI 2025 · similarity 0.87)
- Can Large Multimodal Models Understand Agricultural Scenes? Benchmarking with AgroMind (NeurIPS 2025 · similarity 0.86)
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.
