Your article is protected by copyright and all rights are held exclusively by Springer-Verlag London Limited. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to selfarchive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12 months after publication.
Traffic sign recognition is an important problem in today's applications. In this paper, by combining ensemble and active learning methods, a novel fusion mixture of active experts algorithm is proposed for this problem. The active learning algorithm is a popular method for reducing the number of samples. The primary goal of active learning is diminishing complexity, increasing the convergence rate, speeding up training process, and decreasing the cost of samples labeling. The active learning, hence, chooses informative samples to train. In addition, ensemble methods are a combination of simple classifiers for improving accuracy. Each classifier tries to learn a region of dataset better than other regions that all opinions are considered on ensemble methods as an ultimate decision. The mixture of experts is one of the most modern hybrid methods in which the training process takes a relatively long time, and it is a problem for large datasets. Our proposed Mixture of Active Experts tries to solve this problem. It decreases the training time process and increases the speed of convergence for finding optimal weights by selecting only informative samples in active learning phase. It is also applicable for online situations, in which the model should be trained continuously. The results of different experiments on German Traffic Sign Recognition Benchmark dataset demonstrate that the proposed method shows 96.69% accuracy and achieved the 6th rank among all the state of the art algorithms using smaller number (only 60%) of training samples.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.