DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting

TL;DR

DINOv3 is evaluated as a frozen backbone for blueberry robotic harvesting-related visual tasks, including fruit and bruise segmentation, as well as fruit and cluster detection, and the failure of cluster detection highlights limitations in modeling relational targets defined by spatial aggregation.

Abstract

Vision Foundation Models trained via large-scale self-supervised learning have demonstrated strong generalization in visual perception; however, their practical role and performance limits in agricultural settings remain insufficiently understood. This work evaluates DINOv3 as a frozen backbone for blueberry robotic harvesting-related visual tasks, including fruit and bruise segmentation, as well as fruit and cluster detection. Under a unified protocol with lightweight decoders, segmentation benefits consistently from stable patch-level representations and scales with backbone size. In contrast, detection is constrained by target scale variation, patch discretization, and localization compatibility. The failure of cluster detection highlights limitations in modeling relational targets defined by spatial aggregation. Overall, DINOv3 is best viewed not as an end-to-end task model, but as a semantic backbone whose effectiveness depends on downstream spatial modeling aligned with fruit-scale and aggregation structures, providing guidance for blueberry robotic harvesting. Code and dataset will be available upon acceptance.

Figures (9)

• Figure 1: Samples of used datasets: (a) Bruising Segmentation; (b) Cluster Detection; (c) Fruit Segmentation; (d) Fruit Detection.
• Figure 2: Workflow of DINOv3-based evaluation framework.
• Figure 3: Structural diagram of Patch-Level Decoders.
• Figure 4: Visualization and PCA for bruising segmentation.
• Figure 5: Segmentation and detection results with PCA analysis for the Blueberry Fruit Segmentation Dataset.