Difference between Model Architecture in the Paper and the Actual Implementation

[michaelku1]

Hello, Thanks for your great work. I would like to point out that in the paper it looks to me that the query features are passed to the CAM module. However, in the actual implementation the query features did not play a role until the final encoder-decoder architecture.

For example, the category_code() also computes the categorical features using the support samples, whereas in the meta_detr.py module the query features are extracted from the backbone and are only interacted with the support features in the self.transformer(), which seems to be different from paper's architecture. I am wondering if something is missing? Thanks.

[nhw649]

I have the same problem.

[NHeLv1]

same question

[NHeLv1]

I found class SingleHeadSiameseAttention seems to be the CAM module, not sure