Swin Transformer V2: Scaling Up Capacity and Resolution
We present techniques for scaling Swin Transformer [35] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up c...
Publications
2 shownVideo Swin Transformer
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition ben...
Frequent Co-Authors
Researcher Info
- h-index
- 2
- Publications
- 2
- Citations
- 3,487
- Institution
- Huazhong University of Science and Technology
External Links
Identifiers
- ORCID
- 0000-0002-2395-3432
Impact Metrics
h-index
2
h-index: Number of publications with at least h citations each.