What parameters are trainable in the Similarity-based Self-matching module?

ChenJiayi68 / DMTNet

3 stars 1 forks source link

What parameters are trainable in the Similarity-based Self-matching module? #2

Closed tqwei05 closed 2 weeks ago

tqwei05 commented 2 weeks ago

Thank you for your great work!

I have a concern regarding the paper. It states that the Similarity-based Self-matching module is trainable and is optimized using the L1 loss. However, since both Fls and Flq are outputs of a frozen feature extractor, followed by masked pooling and averaging operations, I think it is more like a training-free module.

ChenJiayi68 commented 2 weeks ago

Hi! : ) M1L is used as additional supervised information to optimize the later Adaptive Feature Transformation module through L1 loss.