Skip to main content
Journal cover image

BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection.

Publication ,  Journal Article
Yang, Z; Soltanian-Zadeh, S; Farsiu, S
Published in: Pattern recognition
January 2022

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Pattern recognition

DOI

ISSN

0031-3203

Publication Date

January 2022

Volume

121

Start / End Page

108231

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4605 Data management and data science
  • 4603 Computer vision and multimedia computation
  • 0906 Electrical and Electronic Engineering
  • 0806 Information Systems
  • 0801 Artificial Intelligence and Image Processing
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Yang, Z., Soltanian-Zadeh, S., & Farsiu, S. (2022). BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection. Pattern Recognition, 121, 108231. https://doi.org/10.1016/j.patcog.2021.108231
Yang, Ziyun, Somayyeh Soltanian-Zadeh, and Sina Farsiu. “BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection.Pattern Recognition 121 (January 2022): 108231. https://doi.org/10.1016/j.patcog.2021.108231.
Yang Z, Soltanian-Zadeh S, Farsiu S. BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection. Pattern recognition. 2022 Jan;121:108231.
Yang, Ziyun, et al. “BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection.Pattern Recognition, vol. 121, Jan. 2022, p. 108231. Epmc, doi:10.1016/j.patcog.2021.108231.
Yang Z, Soltanian-Zadeh S, Farsiu S. BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection. Pattern recognition. 2022 Jan;121:108231.
Journal cover image

Published In

Pattern recognition

DOI

ISSN

0031-3203

Publication Date

January 2022

Volume

121

Start / End Page

108231

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4611 Machine learning
  • 4605 Data management and data science
  • 4603 Computer vision and multimedia computation
  • 0906 Electrical and Electronic Engineering
  • 0806 Information Systems
  • 0801 Artificial Intelligence and Image Processing