CASIA OpenIR  > 模式识别国家重点实验室
Blind image quality assessment via learnable attention-based pooling
Gu, Jie1,2; Meng, Gaofeng1; Xiang, Shiming1,2; Pan, Chunhong1
Source PublicationPATTERN RECOGNITION
ISSN0031-3203
2019-07-01
Volume91Pages:332-344
Corresponding AuthorMeng, Gaofeng(gfmeng@nlpr.ia.ac.cn)
AbstractMany recent algorithms based on convolutional neural network (CNN) for blind image quality assessment (BIQA) share a common two-stage structure, i.e., local quality measurement followed by global pooling. In this paper, we mainly focus on the pooling stage and propose an attention-based pooling network (APNet) for BIQA. The core idea is to introduce a learnable pooling that can model human visual attention in a data-driven manner. Specifically, the APNet is built by incorporating an attention module and allows for a joint learning of local quality and local weights. It can automatically learn to assign visual weights while generating quality estimations. Moreover, we further introduce a correlation constraint between the estimated local quality and attention weight in the network to regulate the training. The constraint penalizes the case in which the local quality estimation on a region attracting more attention differs a lot from the overall quality score. Experimental results on benchmark databases demonstrate that our APNet achieves state-of-the-art prediction accuracy. By yielding an attention weight map as by-product, our model gives a better interpretability on the learned pooling. (C) 2019 Elsevier Ltd. All rights reserved.
KeywordImage quality assessment Perceptual image quality Visual attention Convolutional neural network Learnable pooling
DOI10.1016/j.patcog.2019.02.021
WOS KeywordPERCEPTUAL IMAGE ; VISUAL-ATTENTION ; SCORES
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; Beijing Natural Science Foundation[L172053]
Funding OrganizationNational Natural Science Foundation of China ; Beijing Natural Science Foundation
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000466250400027
PublisherELSEVIER SCI LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23709
Collection模式识别国家重点实验室
Corresponding AuthorMeng, Gaofeng
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Gu, Jie,Meng, Gaofeng,Xiang, Shiming,et al. Blind image quality assessment via learnable attention-based pooling[J]. PATTERN RECOGNITION,2019,91:332-344.
APA Gu, Jie,Meng, Gaofeng,Xiang, Shiming,&Pan, Chunhong.(2019).Blind image quality assessment via learnable attention-based pooling.PATTERN RECOGNITION,91,332-344.
MLA Gu, Jie,et al."Blind image quality assessment via learnable attention-based pooling".PATTERN RECOGNITION 91(2019):332-344.
Files in This Item: Download All
File Name/Size DocType Version Access License
PR_online.pdf(3081KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gu, Jie]'s Articles
[Meng, Gaofeng]'s Articles
[Xiang, Shiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gu, Jie]'s Articles
[Meng, Gaofeng]'s Articles
[Xiang, Shiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gu, Jie]'s Articles
[Meng, Gaofeng]'s Articles
[Xiang, Shiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PR_online.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.