Residual‐wider convolutional neural network for image recognition

Abstract

Recent works show that the performance of convolutional neural networks (CNNs) could be improved by making the network wider and introducing residual connections. For example, the Inception architecture is one of the classical models. However, the structure of the series of Inception is complex, and there are more convolution layers and existing redundant image feature information. In order to further improve the performance and observability of CNNs, a novel type of network structure based on two modules, wider module and residual module, is proposed to make full advantage of the information of the image and learn more abundant features in this study, which is called residual-wider network (R-WN). The structure of R-WN is easy to understand and adopts modular design method. Experiential results demonstrate that the proposed R-WN with optimal structure and much fewer convolution layers could achieve much better image recognition results on four classical open data sets (MNIST, CIFAR10, SVHN, and Oxford Flowers 17).

The Immune Depth Presentation Convolutional Neural Network Used for Oil and Gas Pipeline Fault Diagnosis

“…Reference [5] proposed a network architecture based on two modules: wider modules and residual modules, which fully exploited image information to learn richer features and achieved better recognition results on four classical open datasets. Reference [6] introduced a multi-branch cross-connection CNN, which effectively fused features from various branches, improving recognition performance.…”