[DEIMv2] Real Time Object Detection Meets DINOv3

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.

A repository to apply DINOv3 models for different downstream tasks: image classification, semantic segmentation, object detection.

Integrating SAM2 with DINOv2/v3 for segmentation

Command-line tool for extracting DINOv3, CLIP, SigLIP2, RADIO, features for images and videos

dinov3例子

Gaze-LLE-DINOv3: Gaze Target Estimation via Large-Scale Learned Encoders with DINOv3.

Switch the backbone of mask2former to DINOv3 for instance segmentation

Adapting DINOv3 to downstream segmentation tasks

The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

[DEIMv2] Real Time Object Detection Meets DINOv3 C++ and ONNX version

unofficial JAX implementation of DINOv3, translated in full from the original Meta PyTroch reference implementation (Meta please don't sue me)

Lightweight head for depth estimation using DINOv3 as backbone

Dinov3 exploration (use cases & capabilities )

Open-source desktop app for AI-powered animal behavior analysis. v3 (beta) is actively developed and recommended for new projects. For published, reproducible code, use v2-stable.

A PyTorch implementation of an image classification system based on the DINOv3 (self-DIstillation with NO labels) vision transformer. This project provides a complete training pipeline with distributed data parallel (DDP) support, advanced data augmentation, and multiple loss functions including supervised contrastive learning.

Lightweight head for semantic segmentation using DINOv3 as backbone

Lightweight head for object detection using DINOv3 as backbone