DINOv3¶
Authors: Oriane Simeoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michael Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothee Darcet, Theo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Herve Jegou, Patrick Labatut, Piotr Bojanowski
Published: 2025 (Technical Report)
Source: arXiv
Algorithm: DINOv3
arXiv: 2508.10104
Summary¶
DINOv3 is a technical report on scaling self-supervised vision pretraining into a family of dense-feature foundation models. Its most distinctive methodological contribution is Gram anchoring, which addresses degradation of dense feature maps during long training, while the system-level contribution is a suite of models and post-hoc adaptations that work across natural images, aerial imagery, dense prediction, and text-aligned zero-shot use without task-specific fine-tuning.
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.
Links¶
Primary
Standard
Alternate
Tags¶
-
Self-supervised learning
-
Vision foundation models
-
Computer vision
-
DINOv3
-
Dense features
-
Gram anchoring
-
Model scaling
-
Image representation learning
-
Transfer learning
-
Remote sensing