Multiple classifier for concatenate-designed neural network

• Published in: Neural computing & applications Vol. 34; no. 2; pp. 1359 - 1372
• Main Authors: Chan, Ka-Hou, Im, Sio-Kei, Ke, Wei
• Format: Journal Article
• Language: English
• Published: London Springer London 2022; Springer Nature B.V
• Subjects: Artificial Intelligence; Classification; Classifiers; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Convergence; Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Neural networks; Original Article; Performance enhancement; Probability and Statistics in Computer Science; Multiple classifier; Concatenate-designed neural network; Convergence enhancement; normalization; Softplus
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-021-06462-0

This article introduces a multiple classifier method to improve the performance of concatenate-designed neural networks, such as ResNet and DenseNet, with the purpose of alleviating the pressure on the final classifier. We give the design of the classifiers, which collects the features produced between the network sets, and present the constituent layers and the activation function for the classifiers, to calculate the classification score of each classifier. We use the L 2 e x normalization method to obtain the classifier score instead of the Softmax normalization. We also determine the conditions that can enhance convergence. As a result, the proposed classifiers are able to improve the accuracy in the experimental cases significantly and show that the method not only has better performance than the original models, but also produces faster convergence. Moreover, our classifiers are general and can be applied to all classification related concatenate-designed network models.