Deep neural network method based on space fusion pooling

Abstract

The invention relates to a deep neural network method based on space fusion pooling. The method, which is used in image classification, includes the following steps: collecting images of various categories, and marking the category of each image as image tag information; carrying out image set division: dividing the collected images into a training set, a verification set and a test set, wherein the training set is used to train a convolutional neural network; designing a deep neural network structure for image classification (including the number of convolution layers and the number of space fusion pooling layers used), designing the number of filters in the convolution layers, designing the fusion function form, space sliding step length, pooling function, pooling window size and step length in the space fusion pooling layers, designing a convolutional filter structure for feature fusion, designing the number of network training loop iterations and the network convergence conditions, and initializing the network parameters; and inputting training data to the network in batches for calculating and training.

Description

technical field [0001] The invention relates to a method for high-performance image recognition classification and object recognition in the field of computer vision, in particular to a method for image recognition classification and object recognition using a deep learning method. Background technique [0002] In recent years, deep learning technology has been widely used in multiple tasks such as image classification, semantic segmentation and object detection, and automatic driving in the field of computer vision. As an important implementation method in deep learning technology, deep convolutional neural network has achieved remarkable results in many tasks. [0003] Deep convolutional neural networks are often composed of multi-layer convolutional layers and pooling layers. The convolutional layer contains filter parameters for feature extraction, and the pooling layer is used to maintain the translation invariance of the neural network and reduce the impact of data dis...

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to solve the problem that the pooling layer of the existing deep convolutional neural network cannot effectively extract deep-level features, and propose a deep convolutional neural network method based on spatial fusion pooling suitable for image classification. The channel (spatial) information between channels extracts more representative features, and at the same time, through the fusion of spatial information, the number of feature channels is reduced to further improve the efficiency of the neural network

Images