How can you use a Transformer model as a backbone? No documentation available

[deshwalmahesh]

Hey,
Just wanted to know that how could you use a pre-trained Transformer model for object detection? I want to use Microsoft's DiT. Seems like they have used it with Detectron2 but no clear steps have been described. Can you please let me know about where can I find the blog / tutorial / documentation on how to fine tune that transformer architecture to use it as a detection backbone with Faster RCNN / Cascade RCNN.

Thanks in advance :)

[ZawarK7]

Hey,
it has been a long time. Have you implemented the transformer backbone? I am currently using ViT with Faster R-CNN. Let me know if you have implemented it or if you need any help.