An Ensemble of Convolutional Neural Networks for Image Classification Based on LSTM

Convolutional neural networks (CNN) have made significant breakthroughs in image feature extraction. A variety of CNN architectures have been proposed and then continued to be im-proved. However, the representation of image features by a single CNN structure is not comprehensive enough. For example, shal-low CNN extraction is more general and less sensitive, vice versa. In this paper, we propose an ensemble method using LSTM to obtain image features that represent the image more comprehen-sive. We use the output of a single CNN model as an input for LSTM for a moment to ensemble. We evaluated our approach using VGG and other models on the Cifar10 and Cifar100 da-tasets. The accuracy of classification using ensemble features is significantly higher than that of a single model.