DINOv3

TL;DR

DINOv3 is a versatile self-supervised vision model that scales effectively, introduces Gram anchoring to improve dense feature maps, and outperforms state-of-the-art models across many vision tasks without fine-tuning.

Contribution

The paper presents DINOv3, a new self-supervised learning method that leverages scaling, a novel Gram anchoring technique, and post-hoc strategies to enhance model flexibility and performance.

Findings

Outperforms specialized state-of-the-art models across various tasks.

Produces high-quality dense features for diverse vision applications.

Demonstrates effectiveness without fine-tuning across multiple datasets.

Abstract

Self-supervised learning holds the promise of eliminating the need for manual data annotation, enabling models to scale effortlessly to massive datasets and larger architectures. By not being tailored to specific tasks or domains, this training paradigm has the potential to learn visual representations from diverse sources, ranging from natural to aerial images -- using a single algorithm. This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies. First, we leverage the benefit of scaling both dataset and model size by careful data preparation, design, and optimization. Second, we introduce a new method called Gram anchoring, which effectively addresses the known yet unsolved issue of dense feature maps degrading during long training schedules. Finally, we apply post-hoc strategies that further enhance our models' flexibility with respect to resolution, model size, and alignment with text. As a result, we present a versatile vision foundation model that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previous self- and weakly-supervised foundation models. We also share the DINOv3 suite of vision models, designed to advance the state of the art on a wide spectrum of tasks and data by providing scalable solutions for diverse resource constraints and deployment scenarios.