You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for your exciting work! I have two questions about the temporal feature aggregation:
Does the AFFM use deformable attention, or only use original attention?
Does the AFFM shared parameters? Suppose I have temporal BEV features at {T, T-1, T-2}, and I need 4 AFFM to finish the temporal aggregation as introduced in section3.2. Does these 4 AFFM shared parameters? Or I need to initiate 4 attention modules with different parameters?
Looking forward to your reply.
The text was updated successfully, but these errors were encountered:
All AFFMs of the forward process share parameters, and all AFFMs of the reverse process share parameters, so only two AFFM modules need to be instantiated.
Thanks for your exciting work! I have two questions about the temporal feature aggregation:
Looking forward to your reply.
The text was updated successfully, but these errors were encountered: