MV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yi, Jinhui, Luo, Yanan, Deichmann, Marion, Schaaf, Gabriel, Gall, Juergen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909302455795712
author Yi, Jinhui
Luo, Yanan
Deichmann, Marion
Schaaf, Gabriel
Gall, Juergen
author_facet Yi, Jinhui
Luo, Yanan
Deichmann, Marion
Schaaf, Gabriel
Gall, Juergen
contents An early, non-invasive, and on-site detection of nutrient deficiencies is critical to enable timely actions to prevent major losses of crops caused by lack of nutrients. While acquiring labeled data is very expensive, collecting images from multiple views of a crop is straightforward. Despite its relevance for practical applications, unsupervised domain adaptation where multiple views are available for the labeled source domain as well as the unlabeled target domain is an unexplored research area. In this work, we thus propose an approach that leverages multiple camera views in the source and target domain for unsupervised domain adaptation. We evaluate the proposed approach on two nutrient deficiency datasets. The proposed method achieves state-of-the-art results on both datasets compared to other unsupervised domain adaptation methods. The dataset and source code are available at https://github.com/jh-yi/MV-Match.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00903
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies
Yi, Jinhui
Luo, Yanan
Deichmann, Marion
Schaaf, Gabriel
Gall, Juergen
Computer Vision and Pattern Recognition
An early, non-invasive, and on-site detection of nutrient deficiencies is critical to enable timely actions to prevent major losses of crops caused by lack of nutrients. While acquiring labeled data is very expensive, collecting images from multiple views of a crop is straightforward. Despite its relevance for practical applications, unsupervised domain adaptation where multiple views are available for the labeled source domain as well as the unlabeled target domain is an unexplored research area. In this work, we thus propose an approach that leverages multiple camera views in the source and target domain for unsupervised domain adaptation. We evaluate the proposed approach on two nutrient deficiency datasets. The proposed method achieves state-of-the-art results on both datasets compared to other unsupervised domain adaptation methods. The dataset and source code are available at https://github.com/jh-yi/MV-Match.
title MV-Match: Multi-View Matching for Domain-Adaptive Identification of Plant Nutrient Deficiencies
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.00903