Closed yimeng436 closed 10 months ago
I guess deformable-detr just follows the design of Faster-RCNN, which uses an RPN to classify the generated proposals into foreground or background.
That is to say, here the all-zero label, zero represents the foreground ?
That is to say, here the all-zero label, zero represents the foreground ?
Yes
I don't understand why the label label is set to zero when the result of encoder is used to calculate the loss. Can you give me some guidance? Thank you very much