You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your nice study. Why are using (1-target) instead of directly the targets in the focal loss? I am having difficulty in understanding the concept behind that manipulation.
In TopoNet, we utilize focal loss for relationship loss, proposed to address the imbalance between foreground and background predictions in object detection.
Our implementation employs the built-in version of focal loss from mmdet, available here. In this loss calculation, a ground truth class value of 0 indicates the foreground, while 1 refers the background. However, in our the ground truth of adjacent matrix, 1 denotes a positive connection. So the 1 - target operation is utilized for this gap.
Empirically, the gap come from the implement convenience of detection loss and classification loss. In mmdet, some detection loss will use one-hot operation on the class label by default. For instance, if you replace the focal loss to the cross entropy loss in this scenario, this operation is not need.
A related and detailed discussion can be also found in the OpenLane-V2 repo issue #17.
Hello,
Thank you for your nice study. Why are using (1-target) instead of directly the targets in the focal loss? I am having difficulty in understanding the concept behind that manipulation.
TopoNet/projects/toponet/models/dense_heads/relationship_head.py
Line 100 in b933f28
Thanks in advance
The text was updated successfully, but these errors were encountered: