# DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops Source: [DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops]() Collection index: [llms.txt]() Data updated: 2026-03-04T05:00:05.078Z Authors: Boyang Deng, Yuzhen Lu Published: 2026-02-25T22:35:09.000Z ## Abstract Developing robust models for precision vegetable weeding is currently constrained by the scarcity of large-scale, annotated weed-crop datasets. To address this limitation, this study proposes a foundational crop-weed detection model by integrating heterogeneous datasets and leveraging self-supervised learning. A total of 618,642 crop-weed images were initially collected and subsequently refined to 199,388 filtered images for fine-tuning a DINOv3 vision transformer (ViT-small) through a sequential curation strategy. The fine-tuned DINOv3 backbone was then integrated into YOLO26, serving either as a primary backbone or part of a dual-backbone architecture. A feature alignment loss was introduced in the dual backbone framework to enhance feature fusion with minimal computational overhead. Experimental results show that the proposed DINOv3-finetuned ViT-small-based YOLO26-large achieved up to a +5.4% mAP50 gain on in-domain images collected in the 2025 season. Moreover, it demonstrated strong cross-domain generalization with mAP50 improvements of +14.0% on the 2021-2023 season dataset and +11.9% on the 2024 season dataset, compared to the standard YOLO26-large. Although the DINOv3-YOLO26-large model has 45.6% more parameters and a 2.9x increase in inference latency, it maintains real-time performance at ~28.5 frames per second (fps). The curated dataset and software programs developed in this study will be made publicly available. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on Weed Dataset 2025](): Object Detection; Weed Dataset 2025; Precision: 89.6. - [Object Detection on Weed Dataset 2024](): Object Detection; Weed Dataset 2024; Precision: 53.7. - [Object Detection on Weed Dataset 2021-2023](): Object Detection; Weed Dataset 2021-2023; Precision: 65.2. ## Original sources and implementation [Original paper]() [PDF]()