Open QY1994-0919 opened 2 years ago
If you could read Chinese, you may refer to this link: https://github.com/zhanghang1989/PyTorch-Encoding/issues/384#issuecomment-957086497
The mmsegmentation implementation is easier to read https://github.com/open-mmlab/mmsegmentation/blob/master/mmseg/ops/encoding.py#L6
After reading this paper, I was interested in the proposal of visual center in the paper, but I could not find the corresponding code of the specific part? How to choose the codewords (visual centers) ?