Attention guided contextual feature fusion network for salient object detection

作者:

Highlights:

• We propose an attention-guided network for salient object detection.

• Propose an attention module to supervise features from different receptive fields.

• The relationships of contextual features are considered in a more effective way.

• Design a loss function to emphasize misclassified pixel and solve sample imbalance.

摘要

Highlights•We propose an attention-guided network for salient object detection.•Propose an attention module to supervise features from different receptive fields.•The relationships of contextual features are considered in a more effective way.•Design a loss function to emphasize misclassified pixel and solve sample imbalance.

论文关键词:Salient object detection,Fully convolutional neural network,Attention mechanism,Feature fusion

论文评审过程:Received 27 June 2021, Revised 17 September 2021, Accepted 8 November 2021, Available online 13 November 2021, Version of Record 20 November 2021.

论文官网地址:https://doi.org/10.1016/j.imavis.2021.104337