TimeMachine
TimeMachine copied to clipboard
Do you only apply transpose MAMBA under channel independent settings?
Thank you for your outstanding work! I was wondering if the transpose mamba is only applied with variable independent settings. If so, what are your considerations for designing it this way? It seems to me that the mamba transpose is modeling relationships between variables. Looking forward to your answers, thanks again!
Sorry for the delayed response. For channel independence, it meant to capture details in both ways. However, for channel mixing, our experimental results did not provide as much improvement, if considered in transposed way. However, thanks for your interest. We believe that this has more scope to explore further.