DINOv3

• URL: http://arxiv.org/abs/2508.10104v1
• Date: Wed, 13 Aug 2025 18:00:55 GMT
• Title: DINOv3
• Authors: Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski,
• Abstract summary: 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.<n>This technical report introduces DINOv3, a major milestone toward realizing this vision by leveraging simple yet effective strategies.<n>DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks.
• Score: 62.31809406012177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A Survey on Efficient Vision-Language-Action Models [153.11669266922993]
  Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction.<n>Motivated by the urgent need to address these challenges, this survey presents the first comprehensive review of Efficient Vision-Language-Action models.
  arXiv  Detail & Related papers  (2025-10-27T17:57:33Z)
• SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs [29.874597860268008]
  We propose a novel structure aware self supervised learning method for Text Attributed Graphs (SSTAG)<n>By leveraging text as a unified representation medium for graph learning, SSTAG bridges the gap between the semantic reasoning of Large Language Models (LLMs) and the structural modeling capabilities of Graph Neural Networks (GNNs)<n>Our approach introduces a dual knowledge distillation framework that co-distills both LLMs and GNNs into structure-aware multilayer perceptrons (MLPs)<n>Extensive experiments demonstrate that SSTAG outperforms state-of-the-art models on cross-domain transfer learning tasks, achieves
  arXiv  Detail & Related papers  (2025-09-24T09:10:27Z)
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset [140.1967962502411]
  We introduce a novel approach that employs a diffusion transformer to generate semantically rich CLIP image features.<n>A sequential pretraining strategy for unified models-first training on image understanding and subsequently on image generation offers practical advantages.<n>Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models.
  arXiv  Detail & Related papers  (2025-05-14T17:11:07Z)
• POINTS: Improving Your Vision-language Model with Affordable Strategies [28.611705477757454]
  We train a robust baseline model using latest advancements in vision-language models. We filter pre-training data using perplexity, selecting the lowest perplexity data for training. During visual instruction tuning, we used model soup on different datasets when adding more datasets yielded marginal improvements.
  arXiv  Detail & Related papers  (2024-09-07T13:41:37Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Sequential Modeling Enables Scalable Learning for Large Vision Models [120.91839619284431]
  We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. We define a common format, "visual sentences", in which we can represent raw images and videos as well as annotated data sources.
  arXiv  Detail & Related papers  (2023-12-01T18:59:57Z)
• DINOv2: Learning Robust Visual Features without Supervision [75.42921276202522]
  This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.
  arXiv  Detail & Related papers  (2023-04-14T15:12:19Z)
• Active Learning with Pseudo-Labels for Multi-View 3D Pose Estimation [18.768030475943213]
  We improve Active Learning for the problem of 3D pose estimation in a multi-view setting. We develop a framework that allows us to efficiently extend existing single-view AL strategies. We demonstrate additional performance gains by incorporating predicted pseudo-labels, which is a form of self-training.
  arXiv  Detail & Related papers  (2021-12-27T14:34:25Z)
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision [74.9260745577362]
  This paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC) principles. We construct three propagative modules to effectively solve the optimization models with flexible combinations. Experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC.
  arXiv  Detail & Related papers  (2020-12-10T03:24:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.