Hi, thanks for your amazing paper and solid experiments, which proposes a fast, easy-to-deploy, and remarkably performed transformer backbone.
I wonder about the hyrid window sizes. Why did you set 2nd window size N times of 1st window size? In this way, does the model skip inter-window voxel relation between even adjacent window pairs of the first partition?
We utilize the window shift (half of the 1st window size) between the 1st window size and 2nd window size, which introduces connections between even adjacent window pairs of the first partition.
Hi, thanks for your amazing paper and solid experiments, which proposes a fast, easy-to-deploy, and remarkably performed transformer backbone.
I wonder about the hyrid window sizes. Why did you set 2nd window size N times of 1st window size? In this way, does the model skip inter-window voxel relation between even adjacent window pairs of the first partition?