SugarViT -- Multi-objective Regression of UAV Images with Vision Transformers and Deep Label Distribution Learning Demonstrated on Disease Severity Prediction in Sugar Beet

TL;DR

This paper presents SugarViT, a novel Vision Transformer-based framework utilizing Deep Label Distribution Learning for multi-objective regression of UAV imagery, demonstrated on predicting disease severity in sugar beet with integrated environmental data.

Contribution

The work introduces a new multi-objective regression model combining remote sensing data, environmental parameters, and deep learning for plant trait analysis, applicable beyond the specific case.

Findings

Effective disease severity prediction in sugar beet using SugarViT.

Integration of environmental data improves model accuracy.

Framework is adaptable to various image-based regression tasks.

Abstract

Remote sensing and artificial intelligence are pivotal technologies of precision agriculture nowadays. The efficient retrieval of large-scale field imagery combined with machine learning techniques shows success in various tasks like phenotyping, weeding, cropping, and disease control. This work will introduce a machine learning framework for automatized large-scale plant-specific trait annotation for the use case disease severity scoring for Cercospora Leaf Spot (CLS) in sugar beet. With concepts of Deep Label Distribution Learning (DLDL), special loss functions, and a tailored model architecture, we develop an efficient Vision Transformer based model for disease severity scoring called SugarViT. One novelty in this work is the combination of remote sensing data with environmental parameters of the experimental sites for disease severity prediction. Although the model is evaluated on this special use case, it is held as generic as possible to also be applicable to various image-based classification and regression tasks. With our framework, it is even possible to learn models on multi-objective problems as we show by a pretraining on environmental metadata.