Unsupervised Salient Object Detection on Light Field with High-Quality Synthetic Labels

doi:10.1109/TCSVT.2024.3514754

	Unsupervised Salient Object Detection on Light Field with High-Quality Synthetic Labels
	Yanfeng Zheng 1; Zhong Luo 2; Ying Cao3 ; Xiaosong Yang 4; Weiwei Xu 5; Zheng Lin 6; Nan Yin 7; Pengjie Wang 1,4
	2024
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (IF:8.3[JCR-2023],7.1[5-Year])
ISSN	1558-2205
卷号	PP 期号:99
发表状态	已发表
DOI	10.1109/TCSVT.2024.3514754
摘要	Most current Light Field Salient Object Detection (LFSOD) methods require full supervision with labor-intensive pixel-level annotations. Unsupervised Light Field Salient Object Detection (ULFSOD) has gained attention due to this limitation. However, existing methods use traditional handcrafted techniques to generate noisy pseudo-labels, which degrades the performance of models trained on them. To mitigate this issue, we present a novel learning-based approach to synthesize labels for ULFSOD. We introduce a prominent focal stack identification module that utilizes light field information (focal stack, depth map, and RGB color image) to generate high-quality pixel-level pseudo-labels, aiding network training. Additionally, we propose a novel model architecture for LFSOD, combining a multi-scale spatial attention module for focal stack information with a cross fusion module for RGB and focal stack integration. Through extensive experiments, we demonstrate that our pseudo-label generation method significantly outperforms existing methods in label quality. Our proposed model, trained with our labels, shows significant improvement on ULFSOD, achieving new state-of-the-art scores across public benchmarks.
URL	查看原文
收录类别	其他
来源库	IEEE
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/457914
专题	信息科学与技术学院信息科学与技术学院_PI研究组_曹迎组
作者单位	1.Department of Computer Science, Dalian Minzu University, China 2.College of Civil Engineering, Dalian Minzu University, China 3.School of Information Science and Technology, ShanghaiTech University, China 4.National Center for Computer Animation, Bournemouth University, UK 5.State Key Lab of CAD& CG, Department of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China 6.Department of Computer Science and Technology, Tsinghua University, Beijing, China 7.Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE
推荐引用方式 GB/T 7714	Yanfeng Zheng,Zhong Luo,Ying Cao,et al. Unsupervised Salient Object Detection on Light Field with High-Quality Synthetic Labels[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,PP(99).
APA	Yanfeng Zheng.,Zhong Luo.,Ying Cao.,Xiaosong Yang.,Weiwei Xu.,...&Pengjie Wang.(2024).Unsupervised Salient Object Detection on Light Field with High-Quality Synthetic Labels.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,PP(99).
MLA	Yanfeng Zheng,et al."Unsupervised Salient Object Detection on Light Field with High-Quality Synthetic Labels".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY PP.99(2024).