search

xuebinqin / BASNet

Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
MIT License
1.37k stars 250 forks source link

Reproduce the result #31

Closed vandesa003 closed 4 years ago

vandesa003 commented 4 years ago

Hi @NathanUA , thanks for your great work. Recently I am working on Salient object detection and I was trying to re-train BASNet from scratch to benchmark our own work. However I found I cannot reproduce reported result. I got around 0.078 in MAE on DUTS-TE(Trained on DUTS-TR), and I used the evaluation code you provided here https://github.com/NathanUA/Binary-Segmentation-Evaluation-Tool Could you please give me some hint or explanation? thanks in advance!

xuebinqin commented 4 years ago

Did you augment the DUTS-TR with horizontal flipping offline? How long did you trained?

On Fri, Jan 3, 2020 at 10:54 PM vandesa003 notifications@github.com wrote:

Hi @NathanUA https://github.com/NathanUA , thanks for your great work. Recently I am working on Salient object detection and I was trying to re-train BASNet from scratch to benchmark our own work. However I found I cannot reproduce reported result. I got around 0.078 in MAE on DUTS-TE(Trained on DUTS-TR), and I used the evaluation code you provided here https://github.com/NathanUA/Binary-Segmentation-Evaluation-Tool Could you please give me some hint or explanation? thanks in advance!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/NathanUA/BASNet/issues/31?email_source=notifications&email_token=ADSGORMSOFSROYJF2KSJWX3Q4AQDBA5CNFSM4KCUP462YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4ID7ZMIA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORLGCX7H73U2BETHE4LQ4AQDBANCNFSM4KCUP46Q .

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

vandesa003 commented 4 years ago

Yes, I augment the DUTS-TR as the paper mentioned. I trained for around 24 epochs.

xuebinqin commented 4 years ago

The problem could be that your training iteration (24 epochs =~ 60k iterations) is much fewer than that mentioned (400k) in our paper. Please try to train with more iterations. Around 400k(125hrs on 1080ti)should be good.

On Jan 5, 2020, at 6:56 PM, vandesa003 notifications@github.com wrote:

Yes, I augment the DUTS-TR as the paper mentioned. I trained for around 24 epochs.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

vandesa003 commented 4 years ago

@NathanUA Thank you for the reply! I will try it. Just astonished by the learning capability of this network, I thought this many of epochs will make the network overfitting. So is it the Refinement Module enable the further improvement? Anyway, thanks for your hint.