Deep Structured-Output Regression Learning for Computational Color Constancy

Yanlin Qian; Ke Chen; Joni-Kristian Kämäräinen; Jarno  Nikkanen; Jiri Matas

doi:10.1109/ICPR.2016.7899914

Deep Structured-Output Regression Learning for Computational Color Constancy

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

18 Citations (Scopus)

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.

Original language	English
Title of host publication	2016 23rd International Conference on Pattern Recognition (ICPR)
Publisher	IEEE
ISBN (Electronic)	978-1-5090-4847-2
DOIs	https://doi.org/10.1109/ICPR.2016.7899914
Publication status	Published - 2017
Publication type	A4 Article in conference proceedings
Event	International Conference on Pattern Recognition - Duration: 1 Jan 1900 → …

Conference

Conference	International Conference on Pattern Recognition
Period	1/01/00 → …

Publication forum classification

Publication forum level 1

Access to Document

10.1109/ICPR.2016.7899914

Cite this

@inproceedings{7f985aa0cb6d446cb092384abc73d433,

title = "Deep Structured-Output Regression Learning for Computational Color Constancy",

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.",

author = "Yanlin Qian and Ke Chen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen and Jarno Nikkanen and Jiri Matas",

note = "JUFOID=58099; International Conference on Pattern Recognition ; Conference date: 01-01-1900",

year = "2017",

doi = "10.1109/ICPR.2016.7899914",

language = "English",

booktitle = "2016 23rd International Conference on Pattern Recognition (ICPR)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Deep Structured-Output Regression Learning for Computational Color Constancy

AU - Qian, Yanlin

AU - Chen, Ke

AU - Kämäräinen, Joni-Kristian

AU - Nikkanen, Jarno

AU - Matas, Jiri

N1 - JUFOID=58099

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

U2 - 10.1109/ICPR.2016.7899914

DO - 10.1109/ICPR.2016.7899914

M3 - Conference contribution

BT - 2016 23rd International Conference on Pattern Recognition (ICPR)

PB - IEEE

T2 - International Conference on Pattern Recognition

Y2 - 1 January 1900

ER -

Deep Structured-Output Regression Learning for Computational Color Constancy

Abstract

Conference

Publication forum classification

Access to Document

Fingerprint

Cite this