Thanks for your great work! I notice that adding an additional semantic segmentation loss in CondInst could boost the overall performance by about 1 mAP, which is quite a promising result! I want to ask:
where do you add the semantic segmentation loss? After P3 with a 1x1 conv (just like YOLACT) or after F_{mask} or anywhere else?
how do you calculate the semantic segmentation loss? Like YOLACT with sigmoid over 80 classes, or like HTC with 183 classes?
@Scalsol Thank you for your questions. 1) The semantic segmentation task is after P_3 with a few 3x3 conv. layers. 2) We use an 80-class focal loss here.
Thanks for your great work! I notice that adding an additional semantic segmentation loss in CondInst could boost the overall performance by about 1 mAP, which is quite a promising result! I want to ask:
Waiting for your reply!