2025-08-13 · 1,312 citations · club pick

DINOv3

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

Foundation models & pretraining Data collection & teleoperation

arXiv abstract PDF HTML

No peer-reviewed venue on record yet. 1,312 citations, 229 of them influential, as of the last refresh.

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.

Ten-minute slide kit

Six slides is the whole talk: what was broken, what people tried, what these authors did, what the numbers say, where it falls over, and the sentence people should remember.

SLIDE 1

The problem

Foundation models have become a central building block in modern computer vision, enabling broad gen- eralization across tasks and domains through a single, reusable model. Self-supervised learning (SSL) is a powerful approach for training such models, by learning directly from raw pixel data and leveraging the nat- ural co-occurrences of patterns in images. Unlike weakly and fully supervised pretraining methods (Radford et al., 2021; Dehghani et al., 2023; Bolya et al., 2025) which require images paired with…

SLIDE 2

What came before

Self-Supervised Learning Learning without annotations requires an artificial learning task that pro- vides supervision in lieu for training. The art and challenge of SSL lies in carefully designing these so-called pre-text tasks in order to learn powerful representations for downstream tasks. The language domain, by its discrete nature, offers straightforward ways to set up such tasks, which led to many successful unsu- pervised pre-training approaches for text

SLIDE 3

The method

A Family of Models for Multiple Use-Cases We perform knowledge distillation of the ViT-7B model into smaller Vision Transformer variants (ViT-S, ViT-B, and ViT-L), which are highly valued by the com- munity for their improved manageability and efficiency. Our distillation approach uses the same training objective as in the first training phase, ensuring consistency in learning signals. However, instead of relying on an exponential moving average (EMA) of model weights, we use the 7B model directly as the teacher…

SLIDE 4

What they measured

In this section, we evaluate our flagship DINOv3 7B model on a variety of computer vision tasks. Throughout our experiments, unless otherwise specified, we keep DINOv3 frozen and solely use its representations. We demonstrate that with DINOv3, finetuning is not necessary to obtain strong performance. We first probe the quality of DINOv3’s dense (Sec. 6.1) and global (Sec. 6.2) image representations using lightweight evaluation protocols and compare it to the strongest available vision

SLIDE 5

Where it breaks

Not recoverable from the parsed text. Read this section in the paper yourself.

SLIDE 6

One-line takeaway

Keynote 2 by by Arjun Subramaniam (Factory Intelligence)

Assembled from the paper's own PDF, parsed with its layout intact, 267,284 characters of it, then split on the paper's own section headings. Extractive, not generated: every sentence here is lifted from the paper. The takeaway line is the club's own one-liner from its reading list. Check it before you present it.

Figures worth putting on a slide

Figure 1: (a) Evolution of linear probing results on ImageNet1k (IN1k) over the years, comparing fully-
Figure 2: Performance of the DINOv3 family of models, compared to other families of self- or weakly-
Figure 3: High-resolution dense features. We visualize the cosine similarity maps obtained with DI-
Figure 4: DINOv3 at very high resolution. We visualize dense features of DINOv3 by mapping the first
Figure 5: Evolution of the cosine similarities (a) and of the accuracy on ImageNet1k linear (IN1k) and
Figure 6: Evolution of the cosine similarity between the patch noted in red and all other patches. As training

Presented at

Saturday, May 23, 2026

Saturday Robotics, session 9

Robotics & World Models Reading Club 09: CVPR Warm-up & Founders Spotlight — DeltaWorld + VisuoTactile Dexterous Hands | San Francisco 0523

Listed on the event page as “A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens”. The arXiv title above is the record.

San Francisco, CA

Why the club picked it. Keynote 2 by by Arjun Subramaniam (Factory Intelligence)