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.
@article{arxiv.2103.00334,
title = {BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection},
author = {Ziyun Yang and Somayyeh Soltanian-Zadeh and Sina Farsiu},
journal= {arXiv preprint arXiv:2103.00334},
year = {2021}
}
Comments
This paper is accepted by Pattern Recognition. Please cite as following: "Z. Yang, S. Soltanian-Zadeh, and S. Farsiu, "BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection", Pattern Recognition, (In Press) 2021"