Closed ikvision closed 1 year ago
Hi @ikvision , thanks very much for bringing this question up! This is a very reasonable thought and we haven't done serious ablation on that. RevIn would be a little bit difficult after patching, since an extra dimension is introduced.
In the current implementation the forward path first applies normalization and then applies masking. https://github.com/yuqinie98/PatchTST/blob/de8d7f0da12f4af1bfe13de3d7fe0b888bd84ea9/PatchTST_self_supervised/patchtst_supervised.py#L96-L97 Therefore the RevInCB mean and std are calculated on the non-masked inputs. I think the RevInCB normalization can reveal the masked patches and assist the algorithm to recover pattern that are hidden if they are significantly different than the non-masked regions. Is it the intended behavior?