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

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.

Automated summary

Traditional deep learning-based methods view salient object detection as a pixel-wise saliency modeling task, but often lack sufficient utilization of inter-pixel information. To address this limitation, a connectivity-based approach called bilateral connectivity network (BiconNet) is proposed, which has been demonstrated to effectively model inter-pixel relationships and object saliency through comprehensive experiments.