Exploring viewport features for semi-supervised saliency prediction in omnidirectional images

Mengke Huang, Gongyang Li, Zhi Liu, Yong Wu, Chen Gong, Linchao Zhu, Yi Yang

Abstract: Highlights•We propose a VFNet for semi-supervised saliency prediction in omnidirectional images (ODIs).•We propose a new form of perturbation, i.e., DropView, to fully use unlabeled ODIs.•We propose a VFAI module to fit the distribution of visual saliency in different viewports in ODIs.•Our VFNet achieves competitive performance as compared with 10 SOTA methods.