학술논문
Curiously Effective Features For Image Quality Prediction
Document Type
Conference
Author
Source
2021 IEEE International Conference on Image Processing (ICIP) Image Processing (ICIP), 2021 IEEE International Conference on. :1399-1403 Sep, 2021
Subject
Language
ISSN
2381-8549
Abstract
The performance of visual quality prediction models is commonly assumed to be closely tied to their ability to capture perceptually relevant image aspects. Models are thus either based on sophisticated feature extractors carefully designed from extensive domain knowledge or optimized through feature learning. In contrast to this, we find feature extractors constructed from random noise to be sufficient to learn a linear regression model whose quality predictions reach high correlations with human visual quality ratings, on par with a model with learned features. We analyze this curious result and show that besides the quality of feature extractors also their quantity plays a crucial role - with top performances only being achieved in highly overparameterized models.