SiaTrans: Siamese transformer network for RGB-D salient object detection with depth image classification

作者：

Highlights：

• The proposed Siamese transformer structure (SiaTrans) can save space resources and give full play to the GPU computing power.

• SiaTrans can realize RGB SOD task, RGB-D SOD task, and classify depth images according to depth image quality.

• Siatrans uses one network to achieve three visual tasks while the amount of computation and parameters remain at a low level.

摘要

•The proposed Siamese transformer structure (SiaTrans) can save space resources and give full play to the GPU computing power.•SiaTrans can realize RGB SOD task, RGB-D SOD task, and classify depth images according to depth image quality.•Siatrans uses one network to achieve three visual tasks while the amount of computation and parameters remain at a low level.

论文关键词：Transformer,RGB-D salient object detection,Siamese network,Image classification

论文评审过程：Received 20 July 2022, Accepted 26 August 2022, Available online 3 September 2022, Version of Record 21 September 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104549