Cascaded hourglass feature fusing network for saliency detection

doi:10.1016/j.neucom.2020.11.058

CORC > 长春光学精密机械与物理研究所 > 中国科学院长春光学精密机械与物理研究所

	Cascaded hourglass feature fusing network for saliency detection
	H. Luo; G. Han; X. Wu; P. Liu; H. Yang and X. Zhang
刊名	Neurocomputing
	2021
卷号	428 页码:206-217
ISSN号	9252312
DOI	10.1016/j.neucom.2020.11.058
英文摘要	Convolutional neural networks have been widely applied in saliency detection task because of its powerful feature extraction capability. Most of existing saliency detection models have achieved great progress by aggregating the strong multi-level features. However, it is still a challenging task to design the feature fusing strategy because of the various differences between multi-level features. In this paper, we explore the effect of cascaded pooling operations for saliency detection and propose a novel network to decode saliency cues from multi-level features progressively. We refer to the architecture as "cascaded hourglass" feature fusing network. The proposed network equips with three cascaded sub-modules to capture the multi-scale context and integrate multi-level features progressively. Specifically, we first propose a multi-scale context-aware feature extraction block with different dilated convolutional branches to obtain multi-scale context-aware saliency cues. Then, a hourglass feature fusing block with successive steps of pooling operations is applied to convert the features to multiple feature spaces. Furthermore, we stack a serial of the hourglass feature fusing blocks to purify the multi-level coarse features progressively. Finally, we combine the selective features with cascaded feature decoder to produce final saliency map. Extensive experiments demonstrate the proposed network compares favorably against state-of-the-art methods. Additionally, our model is efficient with the real-time speed of 28 FPS when processing a 400300 image. 2020 Elsevier B.V.
URL标识	查看原文
内容类型	期刊论文
源URL	[http://ir.ciomp.ac.cn/handle/181722/65085]
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	H. Luo,G. Han,X. Wu,et al. Cascaded hourglass feature fusing network for saliency detection[J]. Neurocomputing,2021,428:206-217.
APA	H. Luo,G. Han,X. Wu,P. Liu,&H. Yang and X. Zhang.(2021).Cascaded hourglass feature fusing network for saliency detection.Neurocomputing,428,206-217.
MLA	H. Luo,et al."Cascaded hourglass feature fusing network for saliency detection".Neurocomputing 428(2021):206-217.