Expanded Edge Penalty Loss for Salient Object Detection

doi:10.1109/ICICSP54369.2021.9611977

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Expanded Edge Penalty Loss for Salient Object Detection
	Wang, Nan 2; Shi, Yuetian 2; Fang, Jie 1; Yang, Fanchao 2; Zhang, Geng 2; Li, Siyuan 2; Liu, Xuebin 2
	2021
会议日期	2021-09-24
会议地点	Shanghai, China
关键词	RGB images Salient object detection coarse object boundaries expanded edge penalty loss
DOI	10.1109/ICICSP54369.2021.9611977
页码	363-367
英文摘要	As an indispensable preprocessing technique for image understanding, salient object detection aims to extract interesting regions from an image for subsequent processing, which has attracted much attention since its wide range of applications. Recently, with the rapid development of artificial intelligence and machine learning, deep neural network especially deep convolutional neural network based methods have achieved competitive performances because of their strong feature representation capability. However, most of these methods often suffer from coarse boundaries. The main reason is that equal penalty factor is applied to each pixel in the image to optimize the network, but there are huge distinctions in prediction complexity among different ones actually. Specifically, pixels closer to the boundaries are increasingly difficult because of their huge gaps between structural information and semantic label. In these cases, we present an Expanded Edge Penalty Loss (EPL) for salient object detection. EPL gives bigger penalty factors to pixels distributed in boundary and near-boundary regions, and further dynamically adjusts their contributions to the model optimization. In addition, the experimental results on five public and challenging datasets have validated the superiority and effectiveness of the proposed method. © 2021 IEEE.
产权排序	1
会议录	2021 4th International Conference on Information Communication and Signal Processing, ICICSP 2021
会议录出版者	Institute of Electrical and Electronics Engineers Inc.
语种	英语
ISBN号	9781665407571
内容类型	会议论文
源URL	[http://ir.opt.ac.cn/handle/181661/95687]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.School of Communications and Information Engineering School of Artificial Intelligence, Xi'an University of Posts Telecommunications, Shaanxi, Xi'an; 710121, China 2.Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, China;
推荐引用方式 GB/T 7714	Wang, Nan,Shi, Yuetian,Fang, Jie,et al. Expanded Edge Penalty Loss for Salient Object Detection[C]. 见:. Shanghai, China. 2021-09-24.