In the paper, I did't find the description about the pixel-text matching loss. Then I try to find the loss in the open source code, but I fall. In the follow picture, the self.with_identity_head and self.with_auxiliary_head are None, so I just can find the task loss. Please help me. Thank you.
Hi, the pixel-text matching loss is computed using identity head since it already is a classification map and doesn't require a linear classifier head. The head is not None (see here).
In the paper, I did't find the description about the pixel-text matching loss. Then I try to find the loss in the open source code, but I fall. In the follow picture, the self.with_identity_head and self.with_auxiliary_head are None, so I just can find the task loss. Please help me. Thank you.![image](https://github.com/raoyongming/DenseCLIP/assets/72426381/c0393550-4aa9-4a51-8e8e-46d13bcffc26)