Backbone with FPN on top of Swin Transformers
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
🚀 The feature
Adding a backbone with FPN on top of swin transformers similar to the already available resnet_fpn and mobilenet_fpn backbones (https://github.com/pytorch/vision/blob/main/torchvision/models/detection/backbone_utils.py). I do have a working version (need to be confirmed by the authors if it is what was used in the paper for comparisons) in a separate branch. However, as per protocol, I am opening an issue first to see if it is a worthwhile addition.
Motivation, pitch
It lets us use swin transformer based backbones for the object detection frameworks (FasterRCNN, MaskRCNN..).
Alternatives
No response
Additional context
No response
cc @datumbox
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in torchvision/models/detection/backbone_utils.py and compare the existing resnet_fpn and mobilenet_fpn backbones. Read the linked Swin Transformer paper and inspect how the proposed backbone would be used with FasterRCNN and MaskRCNN. Done means the addition is confirmed as worthwhile and supports those object-detection frameworks in line with the paper's comparisons.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100