Hierarchical Curriculum Learning for No-Reference Image Quality Assessment

doi:10.1007/s11263-023-01851-5

	Hierarchical Curriculum Learning for No-Reference Image Quality Assessment
	Wang, Juan 1; Chen, Zewen 1,2; Yuan, Chunfeng1 ; Li, Bing1,5 ; Ma, Wentao 3; Hu, Weiming1,2,4
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN	0920-5691
	2023-07-25
页码	20
通讯作者	Yuan, Chunfeng(cfyuan@nlpr.ia.ac.cn)
摘要	Despite remarkable success has been achieved by convolutional neural networks (CNNs) in no-reference image quality assessment (NR-IQA), there still exist many challenges in improving the performance of IQA for authentically distorted images. An important factor is that the insufficient annotated data limits the training of high-capacity CNNs to accommodate diverse distortions, complicated semantic structures and high-variance quality scores of these images. To address this problem, this paper proposes a hierarchical curriculum learning (HCL) framework for NR-IQA. The main idea of the proposed framework is to leverage the external data to learn the prior knowledge about IQA widely and progressively. Specifically, as a closely-related task with NR-IQA, image restoration is used as the first curriculum to learn the image quality related knowledge (i.e., semantic and distortion information) on massive distorted-reference image pairs. Then multiple lightweight subnetworks are designed to learn human scoring rules on multiple available synthetic IQA datasets independently, and a cross-dataset quality assessment correlation (CQAC) module is proposed to fully explore the similarities and diversities of different scoring rules. Finally, the whole model is fine-tuned on the target authentic IQA dataset to fuse the learned knowledge and adapt to the target data distribution. Experimental results show that our model achieves state-of-the-art performance on multiple standard authentic IQA datasets. Moreover, the generalization of our model is fully validated by the cross-dataset evaluation and the gMAD competition. In addition, extensive analyses prove that the proposed HCL framework is effective in improving the performance of our model.
关键词	No-reference image quality assessment Hierarchical curriculum learning Prior knowledge Cross-dataset quality assessment correlation
DOI	10.1007/s11263-023-01851-5
关键词[WOS]	STATISTICS
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020AAA0106800] ; Natural Science Foundation of China[62202470] ; Natural Science Foundation of China[61972397] ; Natural Science Foundation of China[62122086] ; Natural Science Foundation of China[U1936204] ; Natural Science Foundation of China[62036011] ; Natural Science Foundation of China[62192782] ; Natural Science Foundation of China[61721004] ; Natural Science Foundation of China[U2033210] ; Beijing Natural Science Foundation[4224093] ; Beijing Natural Science Foundation[JQ21017] ; Beijing Natural Science Foundation[L223003] ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research[2017KZDXM081] ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research[2018KZDXM066] ; Guangdong Provincial University Innovation Team Project[2020KCXTD045] ; Youth Innovation Promotion Association, CAS
项目资助者	National Key Research and Development Program of China ; Natural Science Foundation of China ; Beijing Natural Science Foundation ; Major Projects of Guangdong Education Department for Foundation Research and Applied Research ; Guangdong Provincial University Innovation Team Project ; Youth Innovation Promotion Association, CAS
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001035491100001
出版者	SPRINGER
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53856
专题	多模态人工智能系统全国重点实验室
通讯作者	Yuan, Chunfeng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 3.OPPO Corp LTD, Shanghai 201615, Peoples R China 4.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 5.People AI Inc, Beijing 100080, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang, Juan,Chen, Zewen,Yuan, Chunfeng,et al. Hierarchical Curriculum Learning for No-Reference Image Quality Assessment[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2023:20.
APA	Wang, Juan,Chen, Zewen,Yuan, Chunfeng,Li, Bing,Ma, Wentao,&Hu, Weiming.(2023).Hierarchical Curriculum Learning for No-Reference Image Quality Assessment.INTERNATIONAL JOURNAL OF COMPUTER VISION,20.
MLA	Wang, Juan,et al."Hierarchical Curriculum Learning for No-Reference Image Quality Assessment".INTERNATIONAL JOURNAL OF COMPUTER VISION (2023):20.