DINOv2: Learning Robust Visual Features without Supervision.
Maxime OquabTimothée DarcetThéo MoutakanniHuy V. VoMarc SzafraniecVasil KhalidovPierre FernandezDaniel HazizaFrancisco MassaAlaaeldin El-NoubyMido AssranNicolas BallasWojciech GalubaRussell HowesPo-Yao HuangShang-Wen LiIshan MisraMichael RabbatVasu SharmaGabriel SynnaeveHu XuHervé JégouJulien MairalPatrick LabatutArmand JoulinPiotr BojanowskiPublished in: Trans. Mach. Learn. Res. (2024)