面向大规模图像分类的深度卷积神经网络优化

在图像分类任务中，为了获得更高的分类精度，需要对图像提取不同层次的特征信息。深度学习被越来越多的应用于大规模图像分类任务中。本文提出了一种基于深度卷积神经网络的，可应用于大规模图像分类的深度学习框架。该框架在经典的深度卷积神经网络AlexNet基础上分别从网络框架和网络内部结构两个方面对网络做了优化和改进，进一步提升了网络的特征表达能力。同时，通过在全连接层引入隐层使得网络能够同时具备学习图像特征和二值哈希的功能，使得该框架具有处理大规模图像数据的能力。通过在三个标准数据库中的一系列比对实验，分析了不同优化方法在不同情况下的作用，并证明了本文所提优化方法的有效性。

Optimization of Deep Convolutional Neural Network for Large Scale Image Classification

Features from different levels should be extracted from images for more accurate image classification. Deep learning is used more and more in large scale image classification. This paper proposed a deep learning framework based on deep convolutional neural network that could be applied for the large scale image classification. The proposed framework has modified the framework and the internal structure of the classical deep convolutional neural network AlexNet to improve the feature expression ability of the network. Furthermore, this framework has the ability of learning image features and binary hash simultaneously by introducing the hidden layer in the full-connection layer. The proposal has been proved the significance improvement through the serial experiments in three commonly used databases. Furthermore, different effects of different optimization methods are analyzed.