An Efficient Sampling-Based Attention Network for Semantic Segmentation

doi:10.1109/TIP.2022.3162101

	An Efficient Sampling-Based Attention Network for Semantic Segmentation
	He, Xingjian1,2 ; Liu, Jing1,2 ; Wang, Weining2 ; Lu, Hanqing1,2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2022
卷号	31 页码:2850-2863
通讯作者	Liu, Jing(jliu@nlpr.ia.ac.cn)
摘要	Self-attention is widely explored to model long-range dependencies in semantic segmentation. However, this operation computes pair-wise relationships between the query point and all other points, leading to prohibitive complexity. In this paper, we propose an efficient Sampling-based Attention Network which combines a novel sample method with an attention mechanism for semantic segmentation. Specifically, we design a Stochastic Sampling-based Attention Module (SSAM) to capture the relationships between the query point and a stochastic sampled representative subset from a global perspective, where the sampled subset is selected by a Stochastic Sampling Module. Compared to self-attention, our SSAM achieves comparable segmentation performance while significantly reducing computational redundancy. In addition, with the observation that not all pixels are interested in the contextual information, we design a Deterministic Sampling-based Attention Module (DSAM) to sample features from a local region for obtaining the detailed information. Extensive experiments demonstrate that our proposed method can compete or perform favorably against the state-of-the-art methods on the Cityscapes, ADE20K, COCO Stuff, and PASCAL Context datasets.
关键词	Stochastic processes Sampling methods Semantics Image segmentation Computational complexity Pattern recognition Convolution Semantic segmentation stochastic sampling-based attention deterministic sampling-based attention
DOI	10.1109/TIP.2022.3162101
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020AAA0106400] ; National Natural Science Foundation of China[61922086] ; National Natural Science Foundation of China[61872366] ; National Natural Science Foundation of China[U21B2043]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000778905000007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：5[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/173211/48290
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Liu, Jing
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	He, Xingjian,Liu, Jing,Wang, Weining,et al. An Efficient Sampling-Based Attention Network for Semantic Segmentation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:2850-2863.
APA	He, Xingjian,Liu, Jing,Wang, Weining,&Lu, Hanqing.(2022).An Efficient Sampling-Based Attention Network for Semantic Segmentation.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,2850-2863.
MLA	He, Xingjian,et al."An Efficient Sampling-Based Attention Network for Semantic Segmentation".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):2850-2863.

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
An_Efficient_Samplin（3252KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载