search

zwx8981 / UNIQUE

The repository for 'Uncertainty-aware blind image quality assessment in the laboratory and wild' and 'Learning to blindly assess image quality in the laboratory and wild'
Apache License 2.0
127 stars 10 forks source link

About the input size in training and testing time #13

Closed SuperCrystal closed 3 years ago

SuperCrystal commented 3 years ago

In the paper, it is said that during training the input size is set to 384 x 384 for all the images from all the databases, while that during the test, the network will inference on the original size. What if the test size is also 384 x 384? Will this affect the performance?

zwx8981 commented 3 years ago

@SuperCrystal Hi, sorry for the late response. Empirically, testing images with their original size usually delivers better performance than cropping an image patch with 384 x 384 in our experiments.

SuperCrystal commented 3 years ago

@zwx8981 Thanks a lot for your response! Another question is that if std_modeling is False and therefore p = y_diff = y1 - y2 by the code you provided. When I use it in this way, the loss just can not converge. However, if a sigmoid function is used, it can work correctly. Wondering whether you have also test about this. It is really an impressive work anyway :)

xiongxiongtiao commented 3 years ago

Yes，when you set std_modeling to false，you should change the loss function to BCEwithlogit，which inherently contains a sigmoid function. You may also still use the fidelity loss, in which case you should manually append a sigmoid function as you said or fix the std to a constant, say 1, and convert the diff into a probability using the same equation (Thurstone model). Essentially, fidelity loss is used to measure the difference between two probability distributions, so you should first convert the original difference logit into a probability.发自我的iPhone------------------ Original ------------------From: Crystal @.>Date: Wed,Jun 2,2021 7:51 PMTo: zwx8981/UNIQUE @.>Cc: Subscribed @.***>Subject: Re: [zwx8981/UNIQUE] About the input size in training and testingtime (#13) @zwx8981 Thanks a lot for your response! Another question is that if std_modeling is False and therefore p = y_diff = y1 - y2 by the code you provided. When I use it in this way, the loss just can not converge. However, if a sigmoid function is used, it can work correctly. Wondering whether you have also test about this. It is really an impressive work anyway :)

—You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or unsubscribe. [ { @.": "http://schema.org", @.": "EmailMessage", "potentialAction": { @.": "ViewAction", "target": "https://github.com/zwx8981/UNIQUE/issues/13#issuecomment-852961965", "url": "https://github.com/zwx8981/UNIQUE/issues/13#issuecomment-852961965", "name": "View Issue" }, "description": "View this Issue on GitHub", "publisher": { @.": "Organization", "name": "GitHub", "url": "https://github.com" } } ]