What is the effect of replacing transformer with swin transformer?
Hi,
Thanks for your good job!What is the effect of replacing transformer with swin transformer?
Looking forward to your reply~
Hi, thanks for your appreciation in our work. I think that replacing the original transformer with Swin-T may reduce some computational complexity but will not bring performance gain, because the shifted-window attention is an approximation to the full attention. In fact, instead we have tried replacing ResNet with Swin-T as the backbone, this does bring much better performance.
Hi, when you used Swin-T as the backbone, which layers of Swin-T were used in your work? Could you send me the STARK code using Swin-T as the backbone? Thank you very much!