Conv-Former: A Novel Network Combining Convolution and Self-Attention for Image Quality Assessment

doi:10.3390/s23010427

CIOMP OpenIR

	Conv-Former: A Novel Network Combining Convolution and Self-Attention for Image Quality Assessment
	L. Han; H. Lv; Y. Zhao; H. Liu; G. Bi; Z. Yin and Y. Fang
	2023
发表期刊	Sensors
ISSN	14248220
卷号	23 期号:1
摘要	To address the challenge of no-reference image quality assessment (NR-IQA) for authentically and synthetically distorted images, we propose a novel network called the Combining Convolution and Self-Attention for Image Quality Assessment network (Conv-Former). Our model uses a multi-stage transformer architecture similar to that of ResNet-50 to represent appropriate perceptual mechanisms in image quality assessment (IQA) to build an accurate IQA model. We employ adaptive learnable position embedding to handle images with arbitrary resolution. We propose a new transformer block (TB) by taking advantage of transformers to capture long-range dependencies, and of local information perception (LIP) to model local features for enhanced representation learning. The module increases the model’s understanding of the image content. Dual path pooling (DPP) is used to keep more contextual image quality information in feature downsampling. Experimental results verify that Conv-Former not only outperforms the state-of-the-art methods on authentic image databases, but also achieves competing performances on synthetic image databases which demonstrate the strong fitting performance and generalization capability of our proposed model. © 2022 by the authors.
DOI	10.3390/s23010427
URL	查看原文
收录类别	sci ; ei
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/67513
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	L. Han,H. Lv,Y. Zhao,et al. Conv-Former: A Novel Network Combining Convolution and Self-Attention for Image Quality Assessment[J]. Sensors,2023,23(1).
APA	L. Han,H. Lv,Y. Zhao,H. Liu,G. Bi,&Z. Yin and Y. Fang.(2023).Conv-Former: A Novel Network Combining Convolution and Self-Attention for Image Quality Assessment.Sensors,23(1).
MLA	L. Han,et al."Conv-Former: A Novel Network Combining Convolution and Self-Attention for Image Quality Assessment".Sensors 23.1(2023).

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Conv-Former_ A Novel（9493KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载