Pre-Training with Fractal Images Facilitates Learned Image Quality Estimation

Malte Silbernagel, Thomas Wiegand, Peter Eisert, Sebastian Bosse

Abstract

Today’s image quality estimation is widely dominated by learning-based approaches. The availability of annotated, i.e. rated, images is often a bottleneck in training data-driven visual quality models and hinders their generalization power. This paper proposed a novel pre-training scheme for learning-based quality estimation that does not rely on human-annotated datasets, but leverages synthetic fractal images. These images can be synthesized inexhaustibly and are inherently labeled during generation. We evaluate the pre-training strategy on a popular neural network-based quality model and show that the training effort can be reduced significantly, resulting in better final accuracy and faster convergence speed.
BibTeX
@inproceedings{silbernagel2023pre,
  author = {Malte Silbernagel and Thomas Wiegand and Peter Eisert and Sebastian Bosse},
  title = {{Pre-Training with Fractal Images Facilitates Learned Image Quality Estimation}},
  booktitle = {ICIP},
  year = {2023},
  doi = {10.1109/icip49359.2023.10222630},
}

Loading related content...

Figure