DINOv2: Learning Robust Visual Features without Supervision

DINOv2: Learning Robust Visual Features without Supervision

GitHub – facebookresearch/dinov2: PyTorch code and models for the DINOv2 self-supervised learning method.

“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…”

Source: https://dinov2.metademolab.com/

Code: github.com/facebookresearch/dinov2

Paper: https://arxiv.org/abs/2304.07193