DINOv2

A family of foundation models producing universal features suitable for image-level visual tasks (image classification, instance retrieval, video understanding) as well as pixel-level visual tasks (depth estimation, semantic segmentation).

DINOv2 models produce high-performance visual features that can be directly employed with classifiers as simple as linear layers on a variety of computer vision tasks; these visual features are robust and perform well across domains without any requirement for fine-tuning. The models were pretrained on a dataset of 142 M images without using any labels or annotations.