search

xuebinqin / BASNet

Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
MIT License
1.35k stars 249 forks source link

Evaluation on PASCAL-S Dataset #44

Open ftlong6666 opened 3 years ago

ftlong6666 commented 3 years ago

Hello @NathanUA , thank you so much for your works. Here I still confuse how to evaluate your model on PASCAL-S dataset. As we know the pascal dataset Ground-truth is not binarize yet. It has value not only 0 or 255. How to process it and evaluate your model? -Thank you-

xuebinqin commented 3 years ago

There are manually labeled ground truth from Mingming Cheng's Group, what I was using. Many of the papers also use the mean of the each map intensity to binarize the map.

On Sun, Aug 2, 2020 at 10:27 AM ftlong6666 notifications@github.com wrote:

Hello @NathanUA https://github.com/NathanUA , thank you so much for your works. Here I still confuse how to evaluate your model on PASCAL-S dataset. As we know the pascal dataset Ground-truth is not binarize yet. It has value not only 0 or 255. How to process it and evaluate your model? -Thank you-

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/NathanUA/BASNet/issues/44, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORK3DRCSYUZKKLXU6TTR6WHWZANCNFSM4PST5FHA .

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/

ftlong6666 commented 3 years ago

Hello @NathanUA could you give me links where can I download it or paper related to that binarization method?, even if we use the mean, the specific threshold also should be determined. Thank you so much for fast reply.

clelouch commented 3 years ago

@ftlong6666 Ground-truth is available at https://pan.baidu.com/s/106EZWTuY6sFzl3Etflocmg extraction code: rcg2