Saved in:
Bibliographic Details
Main Authors: Schrag, Fabian Dionys, Turkoglu, Mehmet Ozgur, Schindler, Konrad, Stoop, Ralph Lukas
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.25316
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917442965471232
author Schrag, Fabian Dionys
Turkoglu, Mehmet Ozgur
Schindler, Konrad
Stoop, Ralph Lukas
author_facet Schrag, Fabian Dionys
Turkoglu, Mehmet Ozgur
Schindler, Konrad
Stoop, Ralph Lukas
contents Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (Rumex) image classification. We train models on a published, ground vehicle-based dataset (source) and evaluate their performance on a custom target dataset acquired by unmanned aerial vehicles (UAVs). We find that Convolutional Neural Network (CNN) models, specifically ResNets, generalize poorly to the target domain, even after fine-tuning on the source data. Applying moment-matching and maximum classifier discrepancy, two established DA techniques, substantially improves target-domain performance. However, Vision Transformer (ViT) models pretrained with self-supervised objectives (DINOv2, DINOv3) handle domain shifts intrinsically well, surpassing even moment-matching-trained ResNets, likely due to the rich, general-purpose representations acquired during large-scale pretraining. Using ViTs fine-tuned on the source dataset, we demonstrate high classification performances in the range of F1=0.8 on our target dataset. To support further research on DA for weed detection in grassland systems, we publicly release our UAV-based target dataset AGSMultiRumex, comprising data from 15 flights over Swiss meadows.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25316
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Robust Deep Learning-based Rumex Obtusifolius Detection from Drone Images
Schrag, Fabian Dionys
Turkoglu, Mehmet Ozgur
Schindler, Konrad
Stoop, Ralph Lukas
Computer Vision and Pattern Recognition
Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (Rumex) image classification. We train models on a published, ground vehicle-based dataset (source) and evaluate their performance on a custom target dataset acquired by unmanned aerial vehicles (UAVs). We find that Convolutional Neural Network (CNN) models, specifically ResNets, generalize poorly to the target domain, even after fine-tuning on the source data. Applying moment-matching and maximum classifier discrepancy, two established DA techniques, substantially improves target-domain performance. However, Vision Transformer (ViT) models pretrained with self-supervised objectives (DINOv2, DINOv3) handle domain shifts intrinsically well, surpassing even moment-matching-trained ResNets, likely due to the rich, general-purpose representations acquired during large-scale pretraining. Using ViTs fine-tuned on the source dataset, we demonstrate high classification performances in the range of F1=0.8 on our target dataset. To support further research on DA for weed detection in grassland systems, we publicly release our UAV-based target dataset AGSMultiRumex, comprising data from 15 flights over Swiss meadows.
title Towards Robust Deep Learning-based Rumex Obtusifolius Detection from Drone Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.25316