This repo contains extensions to DINO V2 model by Meta AI Research, FAIR, and awesome applications built on top of it. UPDATES COMING SOON!
I AM ACTIVELY WATCHING FOR ANY UPDATES IN THE COMMUNITY AND BUILDING SOMETHING FANCY MYSELF. SO IF THERE IS SOMETHING UP YOU WILL SEE IT HERE FIRST.
DINO V2 has led to a new breakthrough in the field of Computer Vision (CV), and this repository will continue to track and summarize the research progress of DINO V2 in various fields, including Papers/Projects, etc.
If you find this repository helpful, please consider Stars ⭐ or Sharing ⬆️. Thanks.
- 2023.5.4: Add steam-DINO V2 project.
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Reimplementation of Dinov2 for evaluation purpose | Code | - | does not require the XTRANSFORMER library |
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Steam DINOv2: match banners with Meta AI's DINOv2 |  |
Code | - | retrieve Steam games with similar store banners |
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Extract Dataset Feature Vectors with DINOv2 | Colab | Code | - | debug the embedding quality by clustering group of similar images and visualizing them |
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Implementation of instance retrieval using DINOv2 and Faiss | Colab | Code | - | simply provide an image and the model will return similar images based on their features. |
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Finetunig DINOv2 for Unsupervised Image Classification | Code | - | Self supervised image classification on tinyimagenet and imagenet dataset |
| Title | Presentation | Project page | Code base | Affiliation | Description |
|---|---|---|---|---|---|
| Seg-DINOv2 | Code | - | Fine-tuning dino v2 for semantic segmentation task on MSCOCO. |
This template is borrowed from awesome-segment-anything Code
This project is released under the MIT license. Please see the LICENSE file for more information.