2017 IEEE International Conference on Computer Vision (ICCV) (2017)
Oct. 22, 2017 to Oct. 29, 2017
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.182
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.
estimation theory, face recognition, gradient methods, image resolution, learning (artificial intelligence), neural nets, regression analysis
E. Agustsson, R. Timofte and L. V. Gool, "Anchored Regression Networks Applied to Age Estimation and Super Resolution," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2018, pp. 1652-1661.