FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Bing, Zhu, Chen, Han, Dong, Yu, Rui, Cao, Songliang, Wu, Jianhui, Chapman, Scott, Wang, Zijian, Zheng, Bangyou, Guo, Wei, Weiss, Marie, de Solan, Benoit, Hund, Andreas, Roth, Lukas, Norbert, Kirchgessner, Visioni, Andrea, Ge, Yufeng, Li, Wenjuan, Comar, Alexis, Jiang, Dong, Han, Dejun, Baret, Fred, Ding, Yanfeng, Lu, Hao, Liu, Shouyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908525057277952
author Han, Bing
Zhu, Chen
Han, Dong
Yu, Rui
Cao, Songliang
Wu, Jianhui
Chapman, Scott
Wang, Zijian
Zheng, Bangyou
Guo, Wei
Weiss, Marie
de Solan, Benoit
Hund, Andreas
Roth, Lukas
Norbert, Kirchgessner
Visioni, Andrea
Ge, Yufeng
Li, Wenjuan
Comar, Alexis
Jiang, Dong
Han, Dejun
Baret, Fred
Ding, Yanfeng
Lu, Hao
Liu, Shouyang
author_facet Han, Bing
Zhu, Chen
Han, Dong
Yu, Rui
Cao, Songliang
Wu, Jianhui
Chapman, Scott
Wang, Zijian
Zheng, Bangyou
Guo, Wei
Weiss, Marie
de Solan, Benoit
Hund, Andreas
Roth, Lukas
Norbert, Kirchgessner
Visioni, Andrea
Ge, Yufeng
Li, Wenjuan
Comar, Alexis
Jiang, Dong
Han, Dejun
Baret, Fred
Ding, Yanfeng
Lu, Hao
Liu, Shouyang
contents Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the interaction of fine, variable canopy structures with fluctuating field conditions. We present FoMo4Wheat, one of the first crop-domain vision foundation model pretrained with self-supervision on ImAg4Wheat, the largest and most diverse wheat image dataset to date (2.5 million high-resolution images collected over a decade at 30 global sites, spanning >2,000 genotypes and >500 environmental conditions). This wheat-specific pretraining yields representations that are robust for wheat and transferable to other crops and weeds. Across ten in-field vision tasks at canopy and organ levels, FoMo4Wheat models consistently outperform state-of-the-art models pretrained on general-domain dataset. These results demonstrate the value of crop-specific foundation models for reliable in-field perception and chart a path toward a universal crop foundation model with cross-species and cross-task capabilities. FoMo4Wheat models and the ImAg4Wheat dataset are publicly available online: https://github.com/PheniX-Lab/FoMo4Wheat and https://huggingface.co/PheniX-Lab/FoMo4Wheat. The demonstration website is: https://fomo4wheat.phenix-lab.com/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06907
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
Han, Bing
Zhu, Chen
Han, Dong
Yu, Rui
Cao, Songliang
Wu, Jianhui
Chapman, Scott
Wang, Zijian
Zheng, Bangyou
Guo, Wei
Weiss, Marie
de Solan, Benoit
Hund, Andreas
Roth, Lukas
Norbert, Kirchgessner
Visioni, Andrea
Ge, Yufeng
Li, Wenjuan
Comar, Alexis
Jiang, Dong
Han, Dejun
Baret, Fred
Ding, Yanfeng
Lu, Hao
Liu, Shouyang
Computer Vision and Pattern Recognition
Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the interaction of fine, variable canopy structures with fluctuating field conditions. We present FoMo4Wheat, one of the first crop-domain vision foundation model pretrained with self-supervision on ImAg4Wheat, the largest and most diverse wheat image dataset to date (2.5 million high-resolution images collected over a decade at 30 global sites, spanning >2,000 genotypes and >500 environmental conditions). This wheat-specific pretraining yields representations that are robust for wheat and transferable to other crops and weeds. Across ten in-field vision tasks at canopy and organ levels, FoMo4Wheat models consistently outperform state-of-the-art models pretrained on general-domain dataset. These results demonstrate the value of crop-specific foundation models for reliable in-field perception and chart a path toward a universal crop foundation model with cross-species and cross-task capabilities. FoMo4Wheat models and the ImAg4Wheat dataset are publicly available online: https://github.com/PheniX-Lab/FoMo4Wheat and https://huggingface.co/PheniX-Lab/FoMo4Wheat. The demonstration website is: https://fomo4wheat.phenix-lab.com/.
title FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06907