A simple technique for improving multi- class classification with neural networks

  • We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task.

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Thomas Kopinski, Alexander Gepperth, Uwe Handmann
DOI:https://doi.org/https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2015-136.pdf
Parent Title (English):In 23th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2015), Bruges, Belgium
Document Type:Conference Proceeding
Language:English
Year of Completion:2015
Release Date:2019/07/08
Pagenumber:5
First Page:469
Last Page:474
Institutes:Fachbereich 1 - Institut Informatik
DDC class:000 Allgemeines, Informatik, Informationswissenschaft / 000 Allgemeines, Wissenschaft
Licence (German):License LogoNo Creative Commons