This work is very interesting, which provides some theoretical and empirical guidance on the usage of Mamba for researchers. I have a question about what the long sequence means in computer vision. Does it mean more patches or a longer distance between objects?
This work is very interesting, which provides some theoretical and empirical guidance on the usage of Mamba for researchers. I have a question about what the long sequence means in computer vision. Does it mean more patches or a longer distance between objects?