DINOv3
By Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michael Ramamonjisoa and 16 more. 2025
1,140 citations recorded by the source corpus.
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.
View Paper: https://www.semanticscholar.org/paper/b49c1adc847c8e2cb9f1b97358366e4887e532ce
Citations in the corpus
- Sparse Prototype Code Underlies Classification and Prediction Across Modalities (2026, unknown): “Results are presented for DINOv3 7B [Siméoni et al., 2025] representations on ImageNet-1K [Deng et al., 2009], and later replicated in many models and modalities (Sec.”
- Domain Generalization Under Posterior Drift (2025, unknown): “To implement DI-ERM, we use pretrained image foundation models (e.g., CLIP [Radford et al., 2021], DINOv2 [Oquab et al., 2023], DINOv3 [Sim´eoni et al., 2025]) to extract visual features from x , and encode Table 3: Sentiment classification performance on Amazon-WILDS with reviewer-specific context.”
- CLeaR: A Unified Framework for Resolving the Leakage-Degradation Dilemma in Style Transfer (2026, unknown): “We use five VFMs in CLeaR: CLIP [23, 29], CSD-CLIP [34], DINO [31], VGG [32], and Inception [37].”
- LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement (2026, unknown): “Vision-language models have achieved remarkable progress in document understanding tasks [10,12–20,29,41,45–47].”