Recursive multi-model complementary deep fusion for robust salient object detection via parallel sub-networks

作者：

Highlights：

• We utilize parallel sub networks to automatically reveal saliency clues at different spatial levels.

• We propose an end-to-end salient object detection model that learns diversity saliency clues in an iterative manner.

• We also provide a novel selective fusion strategy to fuse multi-model saliency clues for a high-performance salient object detection.

摘要

•We utilize parallel sub networks to automatically reveal saliency clues at different spatial levels.•We propose an end-to-end salient object detection model that learns diversity saliency clues in an iterative manner.•We also provide a novel selective fusion strategy to fuse multi-model saliency clues for a high-performance salient object detection.

论文关键词：Salient object detection,Deep learning,Multi-model fusion

论文评审过程：Received 22 March 2020, Revised 5 July 2021, Accepted 27 July 2021, Available online 3 August 2021, Version of Record 12 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108212