{
  "abstract": "Accurate segmentation of plant disease symptoms is essential for crop monitoring and phenotyping, yet it typically requires costly pixel-level annotations. Weakly supervised semantic segmentation (WSSS) alleviates this burden by relying on cheaper forms of annotation, such as image-level labels, bounding boxes, or point annotations, to produce supervision (pseudo-mask) for training a segmentation model. We investigate whether text-guided segmentation with the Segment Anything Model 3 (SAM3) can serve as an alternative as it directly segments regions matching a text prompt description of the disease symptoms.Three pseudo-mask generation strategies are compared: (i) class activation maps (CAMs) refined with SAM or SAM3, (ii) zero-shot text-guided SAM3, and (iii) a hybrid approach combining weak spatial cues with text prompts. The resulting pseudo-masks are used to train a fully supervised model (DeepLabV3+). Text guidance alone matches or outperforms conventional WSSS, achieving up to 0.46 IoU without spatial supervision and 0.61 IoU on a public dataset, although performance is sensitive to text prompt formulation. The hybrid strategy improves robustness, reaching 0.50 IoU on the primary dataset and 0.58 IoU on the additional dataset while reducing prompt sensitivity. Overall, text guidance is a promising alternative to conventional weak supervision, while hybrid approaches provide a more robust solution for plant disease segmentation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "Romane Dubois"
    },
    {
      "name": "Lydia Bousset"
    },
    {
      "name": "Stéphane Jumel"
    },
    {
      "name": "Melen Leclerc"
    },
    {
      "name": "Nicolas Parisey"
    },
    {
      "name": "Alexis Joly"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ccf2td0e21qxq.bib",
  "cited_by": 0,
  "doi": "10.1016/j.atech.2026.102544",
  "fulltext_url": null,
  "id": "ccf2td0e21qxq",
  "issns": [
    "2772-3755"
  ],
  "landing_url": "https://hal.science/hal-05692432v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.sdv"
    ],
    [
      "hal",
      "1.info.info-ai"
    ],
    [
      "hal",
      "1.info.info-ti"
    ],
    [
      "hal",
      "1.sdv.bv"
    ],
    [
      "hal",
      "2.sdv.bv.pep"
    ],
    [
      "openalex",
      "1110|Smart Agriculture and AI"
    ]
  ],
  "openalex": "W7167888122",
  "pdf_url": "https://hal.science/hal-05692432/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-10",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/ccf2td0e21qxq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:33Z",
      "native_id": "hal-05692432",
      "source": "hal",
      "url": "https://hal.science/hal-05692432v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "hal:1.sdv.bv",
      "subfield": "plant-biology"
    }
  ],
  "title": "Text guidance is powerful but prompt-sensitive for weakly-supervised leaf symptom segmentation",
  "title_text": "Text guidance is powerful but prompt-sensitive for weakly-supervised leaf symptom segmentation",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:33Z",
  "url": "https://research.draconitic.com/paper/ccf2td0e21qxq",
  "venue": "Smart Agricultural Technology",
  "versions": []
}