Anchored Regression Networks Applied to Age Estimation and Super Resolution

作者：Eirikur Agustsson, Radu Timofte, Luc Van Gool · 年份：2017 · DOI：10.1109/iccv.2017.182 · 被引用次数：67 · 研究领域：Face recognition and analysis、Video Surveillance and Tracking Methods、Advanced Image Processing Techniques

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.