the specific role of the decoder in transformer structure about stark HOT 2 OPEN

@ANdong-star Hi, this process is quite similar to that in the DETR decoder. In DETR, 100 object queries interact with the image features output by the encoder. In STARK, one target query interacts with the joint template-search features to extract the target information. Finally the box prediction head integrate the output of the encoder and the decoder to predict the final box results.

from stark.

@ANdong-star Hi, this process is quite similar to that in the DETR decoder. In DETR, 100 object queries interact with the image features output by the encoder. In STARK, one target query interacts with the joint template-search features to extract the target information. Finally the box prediction head integrate the output of the encoder and the decoder to predict the final box results.

got it! thanks!

from stark.