TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Deep Structured-Output Regression Learning for Computational Color Constancy

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2016 23rd International Conference on Pattern Recognition (ICPR)
KustantajaIEEE
ISBN (elektroninen)978-1-5090-4847-2
DOI - pysyväislinkit
TilaJulkaistu - 2017
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaINTERNATIONAL CONFERENCE ON PATTERN RECOGNITION -
Kesto: 1 tammikuuta 1900 → …

Conference

ConferenceINTERNATIONAL CONFERENCE ON PATTERN RECOGNITION
Ajanjakso1/01/00 → …

Tiivistelmä

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.

Julkaisufoorumi-taso