PestScope: Exclusion-Aware Large Multimodal Model for Fine-Grained Agricultural Pest Segmentation
IEEE Transactions on Image Processing · 2026 · 35 · 2034-2049
DOI: 10.1109/tip.2026.3661417 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yang Yang und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Agriculture. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Department of Science and Technology of Jilin Province, titled ``Research on Trusted Large Model Decision-making Technology Driven by Multi-Source Agricultural Mechanism Knowledge.''.
Abstract (Originalsprache)
Reasoning segmentation (RS) interprets implicit textual instructions to accurately segment target regions. This reasoning capability transforms ambiguous non-expert queries into precise pixel-level masks, thereby enabling downstream tasks like area measurement and density analysis with a level of precision unattainable by detection methods. However, existing RS models are not tailored for agriculture and lack domain-specific knowledge, which poses challenges in handling similar pest appearances and small target scales. To bridge this gap, we introduce a fine-grained pest RS task with two subtasks: Pest Discriminative Referring Expression Segmentation (PDRES) and Pest Exclusion Reasoning Segmentation (PERS). Based on this, we propose PestScope, which integrates vision, language, and reasoning for fine-grained pest segmentation. To tackle the exclusion of small non-target pests, we introduce a dedicated [NON] token alongside the standard [SEG] token for target pests. This guides the model to prioritize small target pests and suppress non-target background regions. To further address pest similarity, we propose an Exclusivity Suppression Loss, applying differentiated supervision to [SEG] and [NON] tokens to better separate target and non-target pests. Additionally, we develop an automated dataset construction pipeline to address the scarcity of fine-grained, difficulty-controllable pest RS datasets. It produces 45k and 27.6k image-text-mask samples for the PDRES and PERS tasks, respectively, covering 18 pest categories. Experiments show that in small and similar pest scenarios, integrating PestScope into mainstream models improves average gIoU by 4.28% on PDRES and 6.49% on PERS. For unseen pest categories, gIoU increases by 21.72% and 8.66%, respectively, demonstrating strong generalization. Code and datasets will be available at: https://github.com/aluodaydayup/PestScope.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Department of Science and Technology of Jilin Province
- titled ``Research on Trusted Large Model Decision-making Technology Driven by Multi-Source Agricultural Mechanism Knowledge.''
Zitieren
APA
Yang, Y., Luo, H., Wang, H., Jiang, J., Liu, J., Wei, J., & Fang, M. (2026). PestScope: Exclusion-Aware Large Multimodal Model for Fine-Grained Agricultural Pest Segmentation. IEEE Transactions on Image Processing, 35, 2034-2049. https://doi.org/10.1109/tip.2026.3661417
Vancouver
Yang Y, Luo H, Wang H, Jiang J, Liu J, Wei J, et al. PestScope: Exclusion-Aware Large Multimodal Model for Fine-Grained Agricultural Pest Segmentation. IEEE Transactions on Image Processing. 2026;35:2034-2049. doi:10.1109/tip.2026.3661417
BibTeX
@article{Yang2026,
author = {Yang, Yang and Luo, Huibin and Wang, Haotian and Jiang, Jingchi and Liu, Jie and Wei, Jian and Fang, Ming},
title = {PestScope: Exclusion-Aware Large Multimodal Model for Fine-Grained Agricultural Pest Segmentation},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {2034--2049},
doi = {10.1109/tip.2026.3661417}
}
EUVIMED