Anchored Regression Networks Applied to Age Estimation and Super Resolution

Eirikur Agustsson, Radu Timofte, Luc Van Gool; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1643-1652

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Agustsson_2017_ICCV,
author = {Agustsson, Eirikur and Timofte, Radu and Van Gool, Luc},
title = {Anchored Regression Networks Applied to Age Estimation and Super Resolution},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}