Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.24947 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914228476051456 |
|---|---|
| author | Zhang, Wentao Fang, Tao Lu, Lina Wang, Lifei Zhong, Weihe |
| author_facet | Zhang, Wentao Fang, Tao Lu, Lina Wang, Lifei Zhong, Weihe |
| contents | Accurate and interpretable crop disease diagnosis is essential for agricultural decision-making, yet existing methods often rely on costly supervised fine-tuning and perform poorly under domain shifts. We propose Caption--Prompt--Judge (CPJ), a training-free few-shot framework that enhances Agri-Pest VQA through structured, interpretable image captions. CPJ employs large vision-language models to generate multi-angle captions, refined iteratively via an LLM-as-Judge module, which then inform a dual-answer VQA process for both recognition and management responses. Evaluated on CDDMBench, CPJ significantly improves performance: using GPT-5-mini captions, GPT-5-Nano achieves \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. The framework provides transparent, evidence-based reasoning, advancing robust and explainable agricultural diagnosis without fine-tuning. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_24947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CPJ: Explainable Agricultural Pest Diagnosis via Caption-Prompt-Judge with LLM-Judged Refinement Zhang, Wentao Fang, Tao Lu, Lina Wang, Lifei Zhong, Weihe Computer Vision and Pattern Recognition Computation and Language Accurate and interpretable crop disease diagnosis is essential for agricultural decision-making, yet existing methods often rely on costly supervised fine-tuning and perform poorly under domain shifts. We propose Caption--Prompt--Judge (CPJ), a training-free few-shot framework that enhances Agri-Pest VQA through structured, interpretable image captions. CPJ employs large vision-language models to generate multi-angle captions, refined iteratively via an LLM-as-Judge module, which then inform a dual-answer VQA process for both recognition and management responses. Evaluated on CDDMBench, CPJ significantly improves performance: using GPT-5-mini captions, GPT-5-Nano achieves \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. The framework provides transparent, evidence-based reasoning, advancing robust and explainable agricultural diagnosis without fine-tuning. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis. |
| title | CPJ: Explainable Agricultural Pest Diagnosis via Caption-Prompt-Judge with LLM-Judged Refinement |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2512.24947 |