Attention and boundary guided salient object detection

作者：

Highlights：

• An attention and boundary guided network for salient object detection is proposed.

• We utilize attention mechanism to give importance to meaningful feature channels.

• We propose a boundary localization module to focus on the useful structural details.

• The proposed approach performs competitive against the existing saliency methods.

摘要

•An attention and boundary guided network for salient object detection is proposed.•We utilize attention mechanism to give importance to meaningful feature channels.•We propose a boundary localization module to focus on the useful structural details.•The proposed approach performs competitive against the existing saliency methods.

论文关键词：Salient object detection,Visual saliency,Feature learning,Fully convolutional neural network

论文评审过程：Received 19 September 2019, Revised 28 February 2020, Accepted 3 June 2020, Available online 5 June 2020, Version of Record 13 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107484