Tampere University of Technology

TUTCRIS Research Portal

Deep Structured-Output Regression Learning for Computational Color Constancy

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition (ICPR)
PublisherIEEE
ISBN (Electronic)978-1-5090-4847-2
DOIs
Publication statusPublished - 2017
Publication typeA4 Article in a conference publication
EventInternational Conference on Pattern Recognition -
Duration: 1 Jan 1900 → …

Conference

ConferenceInternational Conference on Pattern Recognition
Period1/01/00 → …

Abstract

The color constancy problem is addressed by structured-output regression on the values of the fully-connected layers of a convolutional neural network. The AlexNet and the VGG are considered and VGG slightly outperformed AlexNet. Best results were obtained with the first fully-connected “fc6” layer and with multi-output support vector regression. Experiments on the SFU Color Checker and Indoor Dataset benchmarks demonstrate that our method achieves competitive performance, outperforming the state of the art on the SFU indoor benchmark.

Publication forum classification

Field of science, Statistics Finland