Next Article in Journal
KQI Performance Evaluation of 3GPP LBT Priorities for Indoor Unlicensed Coexistence Scenarios
Previous Article in Journal
Sky Imager-Based Forecast of Solar Irradiance Using Machine Learning
Previous Article in Special Issue
GC-YOLOv3: You Only Look Once with Global Context Block
Open AccessArticle

Salient Object Detection Combining a Self-Attention Module and a Feature Pyramid Network

Department of Electrical and Electronic Engineering, Imperial College London, London SW7 2AZ, UK
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(10), 1702; https://doi.org/10.3390/electronics9101702
Received: 4 September 2020 / Revised: 30 September 2020 / Accepted: 13 October 2020 / Published: 16 October 2020
(This article belongs to the Special Issue Deep Learning for Computer Vision and Pattern Recognition)
Salient object detection has achieved great improvements by using the Fully Convolutional Networks (FCNs). However, the FCN-based U-shape architecture may cause dilution problems in the high-level semantic information during the up-sample operations in the top-down pathway. Thus, it can weaken the ability of salient object localization and produce degraded boundaries. To this end, in order to overcome this limitation, we propose a novel pyramid self-attention module (PSAM) and the adoption of an independent feature-complementing strategy. In PSAM, self-attention layers are equipped after multi-scale pyramid features to capture richer high-level features and bring larger receptive fields to the model. In addition, a channel-wise attention module is also employed to reduce the redundant features of the FPN and provide refined results. Experimental analysis demonstrates that the proposed PSAM effectively contributes to the whole model so that it outperforms state-of-the-art results over five challenging datasets. Finally, quantitative results show that PSAM generates accurate predictions and integral salient maps, which can provide further help to other computer vision tasks, such as object detection and semantic segmentation. View Full-Text
Keywords: salient object detection; pyramid self-attention module; fully convolution network; feature pyramid network salient object detection; pyramid self-attention module; fully convolution network; feature pyramid network
Show Figures

Figure 1

MDPI and ACS Style

Ren, G.; Dai, T.; Barmpoutis, P.; Stathaki, T. Salient Object Detection Combining a Self-Attention Module and a Feature Pyramid Network. Electronics 2020, 9, 1702.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop