LITv2 icon indicating copy to clipboard operation
LITv2 copied to clipboard

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

Results 3 LITv2 issues
Sort by recently updated
recently updated
newest added

Hi,I tried to use HiLo block on the image restoration task, but I found that the training speed of HiLo is much slower compared to Swin. Specifically, we mainly adopt...

Dear author, I would like to input the data dimensions [2,64,300,64,64] into HiLo, which represent dimension, number of channels, video sequence, height, and width, respectively. But the acceptable data for...