Jungbeom Lee

Hi, You can run "get_mask_quality.sh" for a whole process. More specifically, after obtaining CAM with "obtian_cam_masking.py", you should run "python run_sample.py" to generate the final pseudo ground-truth masks. Thanks

IRN (resnet50_irn) is the network to refine the initial seed (CAM), which is obtained from the classifier (resnet50_cam). So, we first obtain the CAM from resnet50_cam, and then refine the...

I will make our trained segmentation model public, soon. (Maybe in June) Thanks.

Hi @won-bae, Yes, we did use the default setting provided in the official CCT repository.

Sorry for the late reply. We used the multi-scale inference provided by the CCT official repository, and we apply CRFs. You can refer to deeplab-pytorch repository (https://github.com/kazuto1011/deeplab-pytorch) for more details....

Hi @won-bae, sorry for the late reply. Yes, I have applied multi-scale testing on validation images. Thank you.

Hi @YeRen123455 , sorry for the late reply. (1) "resnet50.py" just contains the definitions of layers of resnet50, and actual architectures for classification and CAM are included in "resnet50_cam.py". I...

No, I just apply adversarial climbing only for the (ground-truth) foreground labels.

Thanks ! :D

Sorry for the late reply. You can train your own train by following the original repository of IRN (https://github.com/jiwoon-ahn/irn) Thank you.