BiconNet: An edge-preserved connectivity-based approach for salient object detection

PATTERN RECOGNITION

卷:121

Article

Yang, Ziyun¹  Soltanian-Zadeh, Somayyeh¹  Farsiu, Sina^1,2,3,4 

[1] Duke Univ, Dept Biomed Engn, Durham, NC 27708 USA

[2] Duke Univ, Dept Ophthalmol, Med Ctr, Durham, NC 27710 USA

[3] Duke Univ, Dept Elect & Comp Engn, Durham, NC 27708 USA

[4] Duke Univ, Dept Comp Sci, Durham, NC 27708 USA

关键词: Salient object detection;    Visual saliency;    Connectivity modeling;    Deep learning;    Edge modeling;   

DOI  :  10.1016/j.patcog.2021.108231

来源: Elsevier

【 摘 要 】

Salient object detection (SOD) is viewed as a pixel-wise saliency modeling task by traditional deep learning-based methods. A limitation of current SOD models is insufficient utilization of inter-pixel information, which usually results in imperfect segmentation near edge regions and low spatial coherence. As we demonstrate, using a saliency mask as the only label is suboptimal. To address this limitation, we propose a connectivity-based approach called bilateral connectivity network (BiconNet), which uses connectivity masks together with saliency masks as labels for effective modeling of inter-pixel relationships and object saliency. Moreover, we propose a bilateral voting module to enhance the output connectivity map, and a novel edge feature enhancement method that efficiently utilizes edge-specific features. Through comprehensive experiments on five benchmark datasets, we demonstrate that our proposed method can be plugged into any existing state-of-the-art saliency-based SOD framework to improve its performance with negligible parameter increase. (c) 2021 Elsevier Ltd. All rights reserved.

【 授权许可】

Free