Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG
A controlled study on the example of bViT model applying one weight-tied block $L$ times, which achieves accuracy parity with ViT on 12-lead electrocardiogram (ECG) classification tasks from the PTB-XL dataset under identical training protocols.
P. Olszowiec, Michal Byra, Grzegorz Gruszczynski et al.
· 0 citations