# DINOv3 Visual Representations for Blueberry Perception Toward Robotic Harvesting

arXiv: https://arxiv.org/abs/2603.02419 · HTML: https://mlsanity.com/paper/2603.02419/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [Vision Foundation Models in Remote Sensing: A Survey](https://mlsanity.com/paper/2408.03464/) (2024)
- [A Multimodal Vision Foundation Model for Clinical Dermatology](https://mlsanity.com/paper/2410.15038/) (2024)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series](https://mlsanity.com/paper/2406.19407/) (2024)
- [Center-guided Classifier for Semantic Segmentation of Remote Sensing Images](https://mlsanity.com/paper/2503.16963/) (2025)

## Built on by (most cited first, 2 of 2)

- [Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection](https://mlsanity.com/paper/2604.15065/) (2026)
- [ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest](https://mlsanity.com/paper/2605.15397/) (2026)

## Abstract (arXiv)

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.