CASIA OpenIR  > 模式识别国家重点实验室
No-reference Image Quality Assessment with Reinforcement Recursive List-wise Ranking
Jie, Gu1,2; Gaofeng Meng1; Cheng Da1,2; Shiming Xiang1,2; Chunhong Pan1
2019
Conference NameAAAI Conference on Artificial Intelligence (AAAI19)
Conference Date2019.01.27-2019.02.01
Conference Place美国夏威夷
Abstract

Opinion-unaware no-reference image quality assessment (NR-IQA) methods have received many interests recently because they do not require images with subjective scores for training. Unfortunately, it is a challenging task, and thus far no opinion-unaware methods have shown consistently better performance than the opinion-aware ones. In this paper, we propose an effective opinion-unaware NR-IQA method based on reinforcement recursive list-wise ranking. We formulate the NR-IQA as a recursive list-wise ranking problem which aims to optimize the whole quality ordering directly. During training, the recursive ranking process can be modeled as a Markov decision process (MDP). The ranking list of images can be constructed by taking a sequence of actions, and each of them refers to selecting an image for a specific position of the ranking list. Reinforcement learning is adopted to train the model parameters, in which no ground-truth quality scores or ranking lists are necessary for learning. Experimental results demonstrate the superior performance of our approach compared with existing opinion-unaware NR-IQA methods. Furthermore, our approach can compete with the most effective opinion-aware methods. It improves the state-of-the-art by over 2% on the CSIQ benchmark and outperforms most compared opinion-aware models on TID2013.

Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23710
Collection模式识别国家重点实验室
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Jie, Gu,Gaofeng Meng,Cheng Da,et al. No-reference Image Quality Assessment with Reinforcement Recursive List-wise Ranking[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
gu_Paper136.pdf(475KB)会议论文 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
[Jie, Gu]'s Articles
[Gaofeng Meng]'s Articles
[Cheng Da]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jie, Gu]'s Articles
[Gaofeng Meng]'s Articles
[Cheng Da]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jie, Gu]'s Articles
[Gaofeng Meng]'s Articles
[Cheng Da]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: gu_Paper136.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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