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

Guangyu Ren, Tianhong Dai, Panagiotis Barmpoutis, Tania Stathaki* (Corresponding Author)

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Downloads (Pure)


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.
Original languageEnglish
Article number1702
Number of pages13
JournalElectronics (Switzerland)
Issue number10
Publication statusPublished - 16 Oct 2020

Bibliographical note

This research was funded by the EU H2020 TERPSICHORE project “Transforming Intangible Folkloric Performing Arts into Tangible Choreographic Digital Objects” under the grant agreement 691218.


  • salient object detection
  • pyramid self-attention module
  • fully convolution network
  • feature pyramid network


Dive into the research topics of 'Salient Object Detection Combining a Self-Attention Module and a Feature Pyramid Network'. Together they form a unique fingerprint.

Cite this