Article

Text guidance is powerful but prompt-sensitive for weakly-supervised leaf symptom segmentation

2026-07-10

Abstract excerpt

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 using image-level labels, but its performance depends on the quality of spatial priors such as class activation maps (CAMs). We investigate whether text-guided segmentation with the Segment A...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 7742f70f-70d1-5ce6-9aa7-4c7bd5ac9752
DOI: 10.64898/2026.07.10.737680

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Text guidance is powerful but prompt-sensitive for weakly-supervised leaf symptom segmentationDOI 10.64898/2026.07.10.737680Read

Unsupervised Anomaly Detection in Plant Disease LocalizationSemantic proximity Read

Attention U-Net for Unsupervised Anomaly Detection in Plant Disease LocalizationSemantic proximity Read

Towards high throughput in-field detection and quantification of wheat foliar diseases with deep learningSemantic proximity Read

Bagging Improves the Performance of Deep Learning-Based Semantic Segmentation with Limited Labeled Images: A Case Study of Crop Segmentation for High-Throughput Plant Phenotyping.Semantic proximity Read

Machine Learning for Image Analysis: Leaf Disease Segmentation.Semantic proximity Read

Deep learning architectures for semantic segmentation and automatic estimation of severity of foliar symptoms caused by diseases or pestsSemantic proximity Read

GuavaVision AI: An Explainable Deep Learning Framework for Automated Classification, Lesion Localization, and Segmentation of Guava DiseasesSemantic proximity Read

An Efficient Attention-Gated Hybrid Transformer-CNN Framework for Plant Disease Segmentation In-the-WildSemantic proximity Read

<span class="word">A <span class="word">U-<span class="word">Net <span class="word">Improved <span class="word">Version <span class="word">for <span class="word">Crop <span class="word">and <span class="word">Weed <span class="word">Segmentation <span class="word">from <span class="word">Aerial <span class="word">ImagesSemantic proximity Read

An explainable deep machine vision framework for plant stress phenotyping.Semantic proximity Read

OneRosette to Predict Them All: Single Plant Prompting on a Visual Foundation Model to Segment Symptomatic Arabidopsis Thaliana Time SeriesSemantic proximity Read

From Canopy Images to Organ-Level Disease Assessments: A Scalable Approach to Measure Quantitative Resistance in the FieldSemantic proximity Read