Why is the classification cost in matcher formulated as the positive minus negative?
Godricly opened this issue · 1 comments
Godricly commented
Hi, I'm confused with this part. The computation here is different from the implementation in sigmoid_focal_loss computation. What is the purpose here to use minus sign?
Deformable-DETR/models/matcher.py
Line 81 in 11169a6
Godricly commented
found an explaination in https://arxiv.org/pdf/2304.04742.pdf.