期刊信息
主管单位:国家教育部
主办单位:重庆大学
主  编:
地  址:重庆市沙坪坝正街174号
邮政编码:400030
电  话:023-65102302
电子邮件:xbsg@cqu.edu.cn
国际标准刊号:ISSN 1000-582X
国内统一刊号:CN 50-1044/N
邮发代号:国内78-16 国外 M355
引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
←前一篇|后一篇→ EndNote   BibTeX  过刊浏览    高级检索
本文已被:浏览 617次   下载 384 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于Xception的细粒度图像分类
张潜1,2, 桑军1,2, 吴伟群1,2, 吴中元1,2, 向宏1,2, 蔡斌1,2
1.重庆大学 信息物理社会可信服务计算教育部重点实验室, 重庆 401331;2.重庆大学 软件学院, 重庆 401331
摘要:
细粒度图像分类是对传统图像分类的子类进行更加细致的划分,实现对物体更为精细的识别,它是计算机视觉领域的一个极具挑战的研究方向。通过对现有的细粒度图像分类算法和Xception模型的分析,提出将Xception模型应用于细粒度图像分类任务。用ImageNet分类的预训练模型参数作为卷积层的初始化,然后对图像进行缩放、数据类型转换、数值归一化处理,以及对分类器参数随机初始化,最后对网络进行微调。在公开的细粒度图像库CUB200-2011、Flower102和Stanford Dogs上进行实验验证,得到的平均分类正确率为71.0%、89.9%和91.4%。实验结果表明Xception模型在细粒度图像分类上有很好的泛化能力。由于不需要物体标注框和部位标注点等额外人工标注信息,Xception模型用在细粒度图像分类上具有较好的通用性和鲁棒性。
关键词:  细粒度图像分类  Xception  卷积神经网络  深度学习
DOI:10.11835/j.issn.1000-582X.2018.05.011
分类号:TP311.1
基金项目:国家重点研发计划资助项目(2017YFB0802400)。
Fine-grained image classification based on Xception
ZHANG Qian1,2, SANG Jun1,2, WU Weiqun1,2, WU Zhongyuan1,2, XIANG Hong1,2, CAI Bin1,2
1.Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing University, Chongqing 401331, P. R. China;2.School of Software Engineering, Chongqing University, Chongqing 401331, P. R. China
Abstract:
Fine-grained image classification is a more detailed division of the sub-categories of traditional image classification, which achieves a more sophisticated identification of objects. And it is a very challenging research in the field of computer vision. By analyzing the existing fine-grained image classification algorithm and Xception model, we propose to apply the Xception model to the fine-grained image classification task. Initialization of convolution layers uses pre-training model parameters of ImageNet classification. Then we resize images, transform data type, normalize value, and randomly initialize classifier. Finally, the network is fine-tuned. Our method obtains 71.0%, 89.9% and 91.4% per-image accuracy on the CUB200-2011, Flower102 and Stanford Dogs dataset respectively. The experimental results show that the Xception model has good generalization ability in fine-grained image classification. Because it does not need additional annotation information such as object bounding box and part annotation, the Xception model has good versatility and robustness in fine-grained image classification.
Key words:  fine-grained image classification  Xception  convolutional neural network  deep learning
Copyright@ 2008 All Rights Reserved.