当前位置: X-MOL 学术Opt. Mem. Neural Networks › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Improving the Performance of Convolutional Neural Networks for Image Classification
Optical Memory and Neural Networks Pub Date : 2021-04-19 , DOI: 10.3103/s1060992x21010100
Davar Giveki

Abstract

As a high performance method for various image processing tasks, deep convolutional neural networks (CNNs) have reached impressive performances and absorbed considerable attention in the last few years. However, object classification on small size datasets for which a limited number of training images is available is still considered as an open problem. In this paper, we investigate a new method to effectively extract semantic image features. The proposed method which is based on CNNs boosts the performance of the object classification problem on small size dataset. To this end, a new method using image segmentation and CNNs is investigated. Our main goal is to increase the classification accuracy by first detecting and then extracting the main object of images. As training CNNs on small datasets does not yield to high performances because of millions of parameters to be learned, we propose using transfer learning strategy. Consequently, we first determine the main object of an image, and then we extract it. The extracted main object is used to tune the weights of the CNN in the training process. In this study, we employ a CNN that has been trained on the ImageNet dataset to reach mid-level image representation. Our experiments on Caltech-101 object dataset have shown that the proposed method substantially defeats other state-of-the-art methods.



中文翻译:

改进卷积神经网络进行图像分类的性能

摘要

作为用于各种图像处理任务的高性能方法,近几年来,深卷积神经网络(CNN)取得了令人印象深刻的性能,并引起了广泛的关注。然而,对于数量有限的训练图像可用的小型数据集的对象分类仍然被认为是一个开放的问题。在本文中,我们研究了一种有效提取语义图像特征的新方法。所提出的基于CNN的方法提高了小尺寸数据集上对象分类问题的性能。为此,研究了一种使用图像分割和CNN的新方法。我们的主要目标是通过先检测然后提取图像的主要对象来提高分类的准确性。由于要学习数百万个参数,因此在小型数据集上训练CNN不能获得高性能,因此我们建议使用转移学习策略。因此,我们首先确定图像的主要对象,然后将其提取。提取的主要对象用于在训练过程中调整CNN的权重。在这项研究中,我们采用了在ImageNet数据集上经过训练的CNN,以达到中等水平的图像表示。我们在Caltech-101对象数据集上的实验表明,所提出的方法大大击败了其他最新技术。在这项研究中,我们采用了在ImageNet数据集上经过训练的CNN,以达到中等水平的图像表示。我们在Caltech-101对象数据集上的实验表明,所提出的方法大大击败了其他最新技术。在这项研究中,我们采用了在ImageNet数据集上经过训练的CNN,以达到中等水平的图像表示。我们在Caltech-101对象数据集上的实验表明,所提出的方法大大击败了其他最新技术。

更新日期:2021-04-19
down
wechat
bug