search

SSL92 / hyperIQA

Source code for the CVPR'20 paper "Blindly Assess Image Quality in the Wild Guided by A Self-Adaptive Hyper Network"
MIT License
361 stars 52 forks source link

regarding the logistic regression before plcc #18

Closed seyeeet closed 3 years ago

seyeeet commented 3 years ago

in the paper mentioned that:

Before calculating PLCC, logistic regression is first
applied to remove nonlinear rating caused by human visual
observation, as suggested in the report from Video Quality
Expert Group (VQEG) [11].

can you please share the logistic regression function that is used?

lllllllllllll-llll commented 3 years ago

Hello, you can use the matlab code for logistic regression. https://github.com/lllllllllllll-llll/SROCC_PLCC_calculate

seyeeet commented 3 years ago

@lllllllllllll-llll thanks, I was hoping to get a python version :p

lllllllllllll-llll commented 3 years ago

@lllllllllllll-llll thanks, I was hoping to get a python version :p Usually, when you do the single database evaluation test (e.g. train on LIVE, test on LIVE), you do not need to do the logistic regression for PLCC. The logistic regression is only applied when you do the cross test evaluation (e.g. train on LIVE, test on CSIQ), which you can use the matlab code.