Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials

arXiv:2508.07514v4 Announce Type: replace-cross Abstract: Reliable plant species and damage segmentation for herbicide field research trials requires models that can withstand substantial real-world variation across seasons, geographies, devices, and sensing modalities. Most deep learning approaches trained on controlled datasets fail to generalize under these domain shifts, limiting their suitability for operational phenotyping pipelines. This study evaluates a segmentation framework that integ