Lightweight transformer and multi-head prediction network for no-reference image quality assessment

被引:0
作者
Zhenjun Tang
Yihua Chen
Zhiyuan Chen
Xiaoping Liang
Xianquan Zhang
机构
[1] Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education
来源
Neural Computing and Applications | 2024年 / 36卷
关键词
Lightweight transformer; Multi-head prediction; Channel attention; Image quality assessment;
D O I
暂无
中图分类号
学科分类号
摘要
No-reference (NR) image quality assessment (IQA) is an important task of computer vision. Most NR-IQA methods via deep neural networks do not reach desirable IQA performance and have bulky models which make them difficult to be used in the practical scenarios. This paper proposes a lightweight transformer and multi-head prediction network for NR-IQA. The proposed method consists of two lightweight modules: feature extraction and multi-head prediction. The module of feature extraction exploits lightweight transformer blocks to learn features at different scales for measuring different image distortions. The module of multi-head prediction uses three weighted prediction blocks and an FC layer to aggregate the learned features for predicting image quality score. The weighted prediction block can measure the importance of different elements of input feature at the same scale. Since the importance of feature elements at the same scale and the importance of the features at different scales are both considered, the module of multi-head prediction can provide more accurate prediction results. Extensive experiments on the standard IQA datasets are conducted. The results show that the proposed method outperforms some baseline NR-IQA methods in IQA performance on the large image datasets. For the model complexity, the proposed method is also superior to several recent NR-IQA methods.
引用
收藏
页码:1931 / 1946
页数:15
相关论文
共 50 条
[41]   No-Reference Image Quality Assessment with Local Gradient Orientations [J].
Oszust, Mariusz .
SYMMETRY-BASEL, 2019, 11 (01)
[42]   CURVELET BASED NO-REFERENCE OBJECTIVE IMAGE QUALITY ASSESSMENT [J].
Shen, Ji ;
Li, Qin ;
Erlebacher, Gordon .
PCS: 2009 PICTURE CODING SYMPOSIUM, 2009, :153-+
[43]   No-reference quality assessment of compressive sensing image recovery [J].
Hu, Bo ;
Li, Leida ;
Wu, Jinjian ;
Wang, Shiqi ;
Tang, Lu ;
Qian, Jiansheng .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 2017, 58 :165-174
[44]   No-Reference Image Quality Assessment for Intelligent Sensing Applications [J].
Yuan, Zhuobin ;
Ikusan, Ademola ;
Dai, Rui ;
Zhang, Junjie .
IEEE NATIONAL AEROSPACE AND ELECTRONICS CONFERENCE, NAECON 2024, 2024, :185-189
[45]   No-reference image quality assessment based on dual-channel convolutional neural network [J].
Huang, Shuyu ;
Sang, Qingbing ;
Wu, Qin ;
Wu, Xiaojun ;
Li, Chaofeng .
2018 INTERNATIONAL SYMPOSIUM IN SENSING AND INSTRUMENTATION IN IOT ERA (ISSI), 2018,
[46]   Dual-Branch Network for No-Reference Super-Resolution Image Quality Assessment [J].
Tang, Tong ;
Yang, Fan ;
Lin, Xinyu ;
Li, Weisheng .
IEEE SIGNAL PROCESSING LETTERS, 2025, 32 :1366-1370
[47]   Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality Assessment [J].
Fu, Jun ;
Hou, Chen ;
Zhou, Wei ;
Xu, Jiahua ;
Chen, Zhibo .
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, :961-969
[48]   No-reference screen content image quality assessment based on multi-region features [J].
Xuhao Jiang ;
Liquan Shen ;
Liangwei Yu ;
Mingxing Jiang ;
Guorui Feng .
NEUROCOMPUTING, 2020, 386 :30-41
[49]   A no-reference perceptual image quality assessment database for learned image codecs [J].
Zhang, Jiaqi ;
Fang, Zhigao ;
Yu, Lu .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2022, 88
[50]   FROM IMAGE QUALITY TO PATCH QUALITY: AN IMAGE-PATCH MODEL FOR NO-REFERENCE IMAGE QUALITY ASSESSMENT [J].
Heng, Wen ;
Jiang, Tingting .
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, :1238-1242