Spatial context-aware network for salient object detection

作者：

Highlights：

• An SCA-Net that explicitly explores and integrates global and local contextual information.

• An LPCM embedded in the endcoding network to grant coarse-scale feature maps better discrimination ability.

• An SPCM in feature decoding to help integrate multi-scale feature maps and compensate saliency predictions with fine detailed cues.

摘要

•An SCA-Net that explicitly explores and integrates global and local contextual information.•An LPCM embedded in the endcoding network to grant coarse-scale feature maps better discrimination ability.•An SPCM in feature decoding to help integrate multi-scale feature maps and compensate saliency predictions with fine detailed cues.

论文关键词：Salient object detection,Context-aware methods,Deep learning

论文评审过程：Received 10 May 2020, Revised 27 November 2020, Accepted 20 December 2020, Available online 2 February 2021, Version of Record 7 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107867