Anchored Regression Networks Applied to Age Estimation and Super Resolution

Eirikur Agustsson, Radu Timofte, Luc Van Gool

ICCV 2017

doi:10.1109/ICCV.2017.182 /iccv/2017/agustsson2017iccv-anchored/

Abstract

We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed. Our ARN is a smoothed relaxation of a piecewise linear regressor through the combination of multiple linear regressors over soft assignments to anchor points. When the anchor points are fixed the optimal ARN regressors can be obtained with a closed form global solution, otherwise ARN admits end-to-end learning with standard gradient based methods. We demonstrate the power of the ARN by applying it to two very diverse and challenging tasks: age prediction from face images and image super-resolution. In both cases, ARNs yield strong results.

PDF ICCV Semantic Scholar

Cite

Text

Agustsson et al. "Anchored Regression Networks Applied to Age Estimation and Super Resolution." International Conference on Computer Vision, 2017. doi:10.1109/ICCV.2017.182

Markdown

[Agustsson et al. "Anchored Regression Networks Applied to Age Estimation and Super Resolution." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/agustsson2017iccv-anchored/) doi:10.1109/ICCV.2017.182

BibTeX

@inproceedings{agustsson2017iccv-anchored,
  title     = {{Anchored Regression Networks Applied to Age Estimation and Super Resolution}},
  author    = {Agustsson, Eirikur and Timofte, Radu and Van Gool, Luc},
  booktitle = {International Conference on Computer Vision},
  year      = {2017},
  doi       = {10.1109/ICCV.2017.182},
  url       = {https://mlanthology.org/iccv/2017/agustsson2017iccv-anchored/}
}