Salient object detection (SOD) in 360$^{\circ }$ omnidirectional images has become an eye-catching problem because of the popularity of affordable 360$^{\circ }$ cameras. In this paper, we propose a Features Adaptation Network (FANet) to highlight salient objects in 360$^{\circ }$ omnidirectional images reliably. To utilize the feature extraction capability of convolutional neural networks and capture global object information, we input the equirectangular 360$^{\circ }$ images and corresponding cube-map 360$^{\circ }$ 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 FENet by 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$^{\circ }$ omnidirectional SOD datasets.

中文翻译：

---

FANet：用于 360° 全方位显着对象检测的自适应网络

360 中的显着物体检测 (SOD)$^{\circ }$ 360度全景的普及成为了一个引人注目的问题$^{\circ }$相机。在本文中，我们提出了一个特征适应网络 (FANet) 来突出 360 度中的显着对象$^{\circ }$可靠的全方位图像。为了利用卷积神经网络的特征提取能力并捕获全局对象信息，我们输入 equirectangular 360$^{\circ }$ 图像和相应的立方体贴图 360$^{\circ }$图像同时传输到特征提取网络 (FENet) 以获得多级等距柱状图和立方体贴图特征。此外，我们通过投影特征适应（PFA）模块在 FENet 的每个级别融合这两种特征，以自适应地选择这两种特征。最后，我们通过多级特征适应（MLFA）模块将不同级别的初步适应特征组合起来，该模块自适应地对这些不同级别的特征进行加权并产生最终的显着图。实验表明，我们的 FANet 在 360 度上优于最先进的方法$^{\circ }$ 全向 SOD 数据集。