Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation


  • Shaoyue Song Beijing Jiaotong University
  • Hongkai Yu University of Texas-Rio Grande Valley
  • Zhenjiang Miao Beijing Jiaotong University
  • Jianwu Fang Chang'an University
  • Kang Zheng University of South Carolina
  • Cong Ma Beijing Jiaotong University
  • Song Wang University of South Carolina



Although there are many existing research works about the salient object detection (SOD) in RGB images, there are still many complex situations that regular RGB images cannot provide enough cues for the accurate SOD, such as the shadow effect, similar appearance between background and foreground, strong or insufficient illumination, etc. Because of the success of near-infrared spectrum in many computer vision tasks, we explore the multi-spectral SOD in the synchronized RGB images and near-infrared (NIR) images for the both simple and complex situations. We assume that the RGB SOD in the existing RGB image datasets could provide references for the multi-spectral SOD problem. In this paper, we first collect and will publicize a large multi-spectral dataset including 780 synchronized RGB and NIR image pairs for the multi-spectral SOD problem in the simple and complex situations. We model this research problem as an adversarial domain adaptation from the existing RGB image dataset (source domain) to the collected multi-spectral dataset (target domain). Experimental results show the effectiveness and accuracy of the proposed adversarial domain adaptation for the multi-spectral SOD.




How to Cite

Song, S., Yu, H., Miao, Z., Fang, J., Zheng, K., Ma, C., & Wang, S. (2020). Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12023-12030.



AAAI Technical Track: Vision