English

Curiously Effective Features for Image Quality Prediction

Computer Vision and Pattern Recognition 2021-06-11 v1

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.

Keywords

Cite

@article{arxiv.2106.05946,
  title  = {Curiously Effective Features for Image Quality Prediction},
  author = {Sören Becker and Thomas Wiegand and Sebastian Bosse},
  journal= {arXiv preprint arXiv:2106.05946},
  year   = {2021}
}

Comments

To be published at ICIP 2021

R2 v1 2026-06-24T03:04:17.287Z