基于数据均衡的增进式深度自动图像标注.PDF

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software ,2017,28(7):18621880 [doi: 10.13328/ki.jos.005112] ©. Tel: +86-10   1,2 1,2 1,2 , , 1( , 350116) 2((), 350116) : , E-mail: kex@ : , ., (stacked auto-encoder, SAE),. , :, (B-SAE),. B-SAE (RB-SAE),,; ,,, ,(SP) ,RB-SAE , (ADA), ,. 3 ,,. : SAE(stacked auto-encoder); ;;; : TP391 : , , . . ,2017,28(7):18621880. /1000-9825/5112.htm : Zhou MK, Ke X, Du MZ. Enhanced deep automatic image annotation based on data equalization. Ruan Jian Xue Bao/Journal of Software, 2017,28(7):18621880 (in Chinese). /1000-9825/5112.htm Enhanced Deep Automatic Image Annotation Based on Data Equalization ZHOU Ming-Ke1,2, KE Xiao1,2, DU Ming-Zhi1,2 1(College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China) 2(Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China) 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 annotat