Why do you still add \( T_{l-1} \) when this addition process is already included in \( V_{im} \)?

hustvl / Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Apache License 2.0

2.55k stars 159 forks source link

Why do you still add \( T_{l-1} \) when this addition process is already included in \( V_{im} \)? #96

Open chriszxk opened 1 week ago

chriszxk commented 1 week ago

Thank you for your excellent work. I have a question regarding equation 6 in the paper: ( Tl = V{im}(T{l-1}) + T{l-1} ). Why do you still add ( T{l-1} ) when this addition process is already included in ( V{im} )?