Hacker News Reader

Could anyone point to an example or git repo showing a simple implementation?

I’m fascinated by this, but am admittedly clueless about how to actually go about building any kind of recognizer or other system atop it.

View on HN

You can pretty much use it as a drop-in replacement for anything built on top of DINOv2. E.g. if you want to fine-tune a segmentation model you can use EoMT[0] which uses DINOv2 as backbone and replace the backbone with DINOv3. If you just want to run it you can give LightlyTrain a spin [1]. There should also be support in the original EoMT repo soon. The methods in the DINOv3 paper focus on frozen backbones which are usually faster to train but might have lower performance than full fine-tuning.

[0]: https://github.com/tue-mps/eomt [1]: https://docs.lightly.ai/train/stable/semantic_segmentation.h...

Their repo has some example notebooks: https://github.com/facebookresearch/dinov3/tree/main/noteboo...

As for doing it in general, it's a fairly standard vision transformer so anything built on DINOv2 (or any other ViT) should be easy to adapt to v3.

Reply on news.ycombinator.com