###
Journal of Software:2017.28(7):1862-1880

基于数据均衡的增进式深度自动图像标注
周铭柯,柯逍,杜明智
(福州大学 数学与计算机科学学院, 福建 福州 350116;福建省网络计算与智能信息处理重点实验室 福州大学, 福建 福州 350116)
Enhanced Deep Automatic Image Annotation Based on Data Equalization
ZHOU Ming-Ke,KE Xiao,DU Ming-Zhi
(College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China;Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing Fuzhou University, Fuzhou 350116, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 1437   Download 1067
Received:January 04, 2016    Revised:May 18, 2016
> 中文摘要: 自动图像标注是一个包含众多标签、多样特征的富有挑战性的研究问题,是新一代图像检索与图像理解的关键步骤.针对传统的基于浅层机器学习标注算法标注效率低下、难以处理复杂分类任务的问题,提出了基于栈式自动编码器(stacked auto-encoder,简称SAE)的自动图像标注算法,提升了标注效率和标注效果.主要针对图像标注数据不平衡问题,提出两种解决思路:对于标注模型,提出一种增强训练中低频标签的平衡栈式自动编码器(B-SAE),较好地改善了中低频标签的标注效果.并在该模型的基础上提出一种分组强化训练B-SAE子模型的鲁棒平衡栈式自动编码器算法(RB-SAE),提升了标注的稳定性,从而保证模型本身具有较强的处理不平衡数据的能力;对于标注过程,以未知图像作为出发点,首先构造未知图像的局部均衡数据集,并判定该图像的高低频属性以决定不同的标注过程,局部语义传播算法(SP)标注中低频图像,RB-SAE算法标注高频图像,形成属性判别的标注框架(ADA),保证了标注过程具有较强的应对不平衡数据的能力,从而提升整体图像标注效果.通过在3个公共数据集上进行实验验证,结果表明,该方法在许多指标上相比以往方法均有较大提高.
Abstract:Automatic image annotation is a challenging research problem involving lots of tags and various features. Aiming at the problem that the image annotation based on the traditional shallow machine learning algorithm has low efficiency and is difficult to apply to complex classification task, this paper proposes an automatic image annotation algorithm based on stacked auto-encoder (SAE) to improve both efficiency and effectiveness of annotation. In this paper, two types of strategies are proposed to solve the main problem of unbalanced data in image annotation. For the annotation model itself, to improve the annotation effect of low frequency tags, a balanced and stacked auto-encoder (B-SAE) that can enhance training for low frequency tags is proposed. Based on this model, a robust balanced and stacked auto-encoder algorithm (RB-SAE) is proposed to increase the annotation stability through enhanced training by group in sub B-SAE model. This strategy ensures that the model itself has a strong ability to deal with the unbalanced data. For the annotation process, taking the unknown image as the starting point, the local equilibrium dataset of the unknown image is constructed, and the high and low frequency attribute of the image is discriminated to determine the different annotation process. The local semantic propagation algorithm (SP) annotates the low frequency images and the RB-SAE algorithm annotates the high frequency images. The framework of attribute discrimination annotation (ADA) is formed to improve the overall image annotation effect. This strategy ensures that the labeling process has a strong ability to deal with unbalanced data. Experimental results generated from three public data sets show that many indicators in the presented model are all improved comparing with the previous models.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61502105);福建省科技引导性项目(2017H0015);福建省中青年教师教育科研项目(JA15075) 国家自然科学基金(61502105);福建省科技引导性项目(2017H0015);福建省中青年教师教育科研项目(JA15075)
Foundation items:National Natural Science Foundation of China (61502105); Technology Guidance Project of Fujian Province, China (2017H0015); Natural Science Foundation of Fujian Provincial Education Department, China (JA15075)
Reference text:

周铭柯,柯逍,杜明智.基于数据均衡的增进式深度自动图像标注.软件学报,2017,28(7):1862-1880

ZHOU Ming-Ke,KE Xiao,DU Ming-Zhi.Enhanced Deep Automatic Image Annotation Based on Data Equalization.Journal of Software,2017,28(7):1862-1880