Discriminative unimodal feature selection and fusion for RGB-D salient object detection

作者：

Highlights：

• We propose a novel RGB-D salient object detection model, which takes the equalities of input into consideration.

• An SG-MWMG sub-network is designed to determine the informative and non-informative regions in the input RGB-D images.

• An MCFF module is designed to fuse the unimodal RGB and depth features at multiple scales and levels.

摘要

•We propose a novel RGB-D salient object detection model, which takes the equalities of input into consideration.•An SG-MWMG sub-network is designed to determine the informative and non-informative regions in the input RGB-D images.•An MCFF module is designed to fuse the unimodal RGB and depth features at multiple scales and levels.

论文关键词：RGB-D salient object detection,Discriminative unimodal feature selection,Semantic information,Multi-scale cross-modal feature fusion

论文评审过程：Received 23 February 2021, Revised 7 July 2021, Accepted 29 September 2021, Available online 1 October 2021, Version of Record 7 October 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108359