SwinTransformer/Transformer-SSL
A PyTorch implementation of self-supervised learning pretraining with Swin Transformer backbones, evaluating learned representations on downstream computer vision tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official implementation of self-supervised learning using vision transformers, specifically Swin Transformer. The project trains models via self-supervision to learn visual representations that transfer well to downstream tasks including object detection, instance segmentation, and semantic segmentation. It achieves competitive ImageNet-1K linear evaluation accuracy using DeiT-S/16 with 300 epoch pretraining while requiring fewer training tricks than comparable approaches like MoCo v3 and DINO.
Frequently asked
- What is SwinTransformer/Transformer-SSL?
- A PyTorch implementation of self-supervised learning pretraining with Swin Transformer backbones, evaluating learned representations on downstream computer vision tasks.
- Is Transformer-SSL open source?
- Yes — SwinTransformer/Transformer-SSL is open source, released under the MIT license.
- What language is Transformer-SSL written in?
- SwinTransformer/Transformer-SSL is primarily written in Python.
- How popular is Transformer-SSL?
- SwinTransformer/Transformer-SSL has 671 stars on GitHub.
- Where can I find Transformer-SSL?
- SwinTransformer/Transformer-SSL is on GitHub at https://github.com/SwinTransformer/Transformer-SSL.