Anzeige
Erschienen in:
2017 | OriginalPaper | Buchkapitel
Shortcut Convolutional Neural Networks for Classification of Gender and Texture
verfasst von : Ting Zhang, Yujian Li, Zhaoying Liu
Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2017
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Convolutional neural networks are global trainable multi-stage architectures that automatically learn translation invariant features from raw input images. However, in tradition they only allow adjacent layers connected, limiting integration of multi-scale information. To further improve their performance in classification, we present a new architecture called shortcut convolutional neural networks. This architecture can concatenate multi-scale feature maps by shortcut connections to form the fully-connected layer that is directly fed to the output layer. We give an investigation of the proposed shortcut convolutional neural networks on gender classification and texture classification. Experimental results show that shortcut convolutional neural networks have better performances than those without shortcut connections, and it is more robust to different settings of pooling schemes, activation functions, initializations, and optimizations.