Abstract
The purpose of saliency detection is to detect significant regions in the image. Great progress on salient object detection has been made using from deep-learning frameworks. How to effectively extract and integrate multiscale information with different depths is an open problem for salient object detection. In this paper, we propose a processing mechanism based on a balanced attention module and interactive residual module. The mechanism addressed the acquisition of the multiscale features by capturing shallow and deep context information. For effective information fusion, a modified bi-directional propagation strategy was adopted. Finally, we used the fused multiscale information to predict saliency features, which were combined to generate the final saliency maps. The experimental results on five benchmark datasets show that the method is on a par with the state of the art for image saliency datasets, especially on the PASCAL-S datasets, where the MAE reaches 0.092, and on the DUT-OMROM datasets, where the F-measure reaches 0.763.
Highlights
Introduction and BackgroundSalient object detection (SOD) aims to localize the most visually obvious regions in an image
Evaluation criteria: We used three metrics to evaluate the performance of the proposed model multiscale balanced-aware interactive network (MBINet) and other state-of-the-art SOD algorithms
For a more comprehensive analysis of interactive residual model (IRM), we further studied the impact of the number of dilate convolutions and the dilation rate
Summary
Salient object detection (SOD) aims to localize the most visually obvious regions in an image. SOD has been used in many computer-vision tasks, such as image retrieval [1,2], visual tracking [3], scene segmentation [4], object recognition [5], image contrast enhancement [6], assisted medicine [7,8,9], etc. The artificially designed features can locate some salient areas, it is difficult to improve the accuracy of salient object detection due to the lack of high-level semantic information. The potential correlation was ignored due to the self-attention mechanism needed to extract deep-feature information
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
