Beom

Why should we use two localization outputs?

2

Hi, I have a question about structure of Faster R-CNN. Why should we use two localization outputs from RPN and Classification Head? I think only localization results from RPN is...

[Question] About dataset condition for MTL

3

Thank you for your awesome work. Your work might be greatly helpful to all people who interest in the MTL. I'm about to study MTL and have one question. I...

Thank you for sharing your great work, GroupRCNN for WSSOD. As in the below figure, GroupRCNN is trained with a subset (10% or 20% or 50%) of COCO fully-labeled datasets....

Could you share pretrained weights using google drive? I cannot access baidu drive... :(

Question about "deeplab_largeFOV.pth"

1

I want to know the source of "deeplab_largeFOV.pth" in data directory, can you explain detail about is?? Is it a pre-trained weight on the ImageNet dataset? or Is it a...

Dear author. Could you provide the instance segmentation AP results on COCO 20% and 50%?