FANet: Features Adaptation Network for 360$^{\circ }$ Omnidirectional Salient Object Detection
Mengke Huang, Zhi Liu, Gongyang Li, Xiaofei Zhou, Olivier Le Meur · IEEE Signal Processing Letters · 2020
Salient object detection (SOD) in 360° omnidirectional images has become an eye-catching problem because of the popularity of affordable 360° cameras. In this paper, we propose a Features Adaptation Network (FANet) to highlight salient objects in 360° omnidirectional images reliably. To utilize the feature extraction capability of convolutional neural networks and capture global object information, we input the equirectangular 360° images and corresponding cube-map 360° images to the feature extraction network (FENet) simultaneously to obtain multi-level equirectangular and cube-map features. Furthermore, we fuse these two kinds of features at each level of the FENetby a projection features adaptation (PFA) module, for selecting these two kinds of features adaptively. Finally, we combine the preliminary adaptation features at different levels by a multi-level features adaptation (MLFA) module, which weights these different-level features adaptively and produces the final saliency maps. Experiments show our FANet outperforms the state-of-the-art methods on the 360° omnidirectional SOD datasets.