BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection
This work addresses edge preservation and spatial coherence issues in salient object detection, which is important for applications like image segmentation, but it is incremental as it builds on existing SOD frameworks.
The paper tackles the problem of imperfect segmentation near edges and low spatial coherence in salient object detection by proposing BiconNet, a connectivity-based approach that uses connectivity masks alongside saliency masks, resulting in improved performance on five benchmark datasets with negligible parameter increase.
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.