arXiv Analytics

Sign in

arXiv:1607.03856 [cs.CV]AbstractReferencesReviewsResources

Deep Structured-Output Regression Learning for Computational Color Constancy

Yanlin Qian, Ke Chen, Joni-Kristian Kamarainen, Jarno Nikkanen, Jiri Matas

Published 2016-07-13Version 1

Computational color constancy that requires esti- mation of illuminant colors of images is a fundamental yet active problem in computer vision, which can be formulated into a regression problem. To learn a robust regressor for color constancy, obtaining meaningful imagery features and capturing latent correlations across output variables play a vital role. In this work, we introduce a novel deep structured-output regression learning framework to achieve both goals simultaneously. By borrowing the power of deep convolutional neural networks (CNN) originally designed for visual recognition, the proposed framework can automatically discover strong features for white balancing over different illumination conditions and learn a multi-output regressor beyond underlying relationships between features and targets to find the complex interdependence of dif- ferent dimensions of target variables. Experiments on two public benchmarks demonstrate that our method achieves competitive performance in comparison with the state-of-the-art approaches.

Related articles: Most relevant | Search more
arXiv:1508.06535 [cs.CV] (Published 2015-08-26)
Deep Convolutional Neural Networks for Smile Recognition
arXiv:1602.03409 [cs.CV] (Published 2016-02-10)
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
arXiv:1601.07255 [cs.CV] (Published 2016-01-27)
PersonNet: Person Re-identification with Deep Convolutional Neural Networks