xuebinqin
commented
4 years ago Yes, you could try to use it for semantic segmentation. Salient object detection is actually binary class image segmentation. To extend it to multi-class semantic segmentation, you have to change the loss computation a little bit to handle multiple classes and replace the last sigmoid of BASNet by softmax.
Best wishes,
On Fri, Dec 27, 2019 at 5:03 AM pp00704831 notifications@github.com wrote:
Hello, because I am interesting in both loss and want to do some experiment. Could both of them directly combined with semantic segmentation? Because this paper is for salient object detection. Thanks You!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/NathanUA/BASNet/issues/30?email_source=notifications&email_token=ADSGORIECPL7AKXXGVVHTL3Q2XVHZA5CNFSM4J73DOVKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IC3I6YA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORN72ZCYBTRHSVUG3ZLQ2XVHZANCNFSM4J73DOVA .
-- Xuebin Qin PhD Candidate Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/
pp00704831
Hello, because I am interesting in both loss and want to do some experiment. Could both of them directly combined with semantic segmentation? Because this paper is for salient object detection. Thanks You!