search

920232796 / NestedFormer

NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation (MICCAI 2022)
Apache License 2.0
39 stars 4 forks source link

Understanding TokenLearner #9

Open AshStuff opened 1 year ago

AshStuff commented 1 year ago

I am trying to understand the tokenlearner and I guess the current implementation is different from the original TokenLearner proposed right ? I guess the original Tokenlearner performs the token learner for each temporal dimension and then reshape back.

920232796 commented 1 year ago

In this work, token learner only controls the sequence length. It doesn't need to reshape back because the network has a segmentation decoder.