Switching network for mixing experts with application to traffic sign recognition

Amir Ahangi*, Rico Möckel

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

The correct and robust recognition of traffic signs is indispensable to self-driving vehicles and driver-assistant systems. In this work, we propose and evaluate two network architectures for multi-expert decision systems that we test on a challenging Traffic Sign Recognition Benchmark dataset. The decision systems implement individual experts in the form of deep convolutional neural networks (CNNs). A gating network CNN acts as final decision unit and learns which individual expert CNNs are likely to contribute to an overall meaningful classification of a traffic sign. The gating network then selects the outputs of those individual expert CNNs to be fused to form the final decision. In this work we study the advantages and challenges of the proposed multi-expert architectures that in comparison to other network architectures allow for parallel training of individual experts with reduced datasets. Under the challenging conditions introduced by the benchmark dataset, the demonstrated multi-expert decision systems achieve a recognition performance that is superior to those of humans: with an accuracy of 99.10%, when training experts with the complete dataset and 98.94%, when individual experts are only trained with 36% of the training samples. Overall, our approach ranked fourth on the list of the applied approaches proposed for the German traffic sign Recognition Benchmark (GTSRB) dataset.
Original languageEnglish
Pages (from-to)43841-43864
Number of pages24
JournalMultimedia Tools and Applications
Volume82
Issue number28
Early online date25 Jan 2023
DOIs
Publication statusPublished - Nov 2023

Keywords

  • Deep learning
  • Ensemble learning
  • Mixture of experts
  • Traffic sign

Fingerprint

Dive into the research topics of 'Switching network for mixing experts with application to traffic sign recognition'. Together they form a unique fingerprint.

Cite this