The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this paper introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320 $\times$ 320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.
翻译:神经网络的高计算成本使得RGB-D显著物体探测(SOD)最近的成功无法从现实世界应用中受益,因此,本文件引入了一个新型网络,即MobileSal,其重点是利用移动网络进行深度地貌提取,高效RGB-D SOD;然而,移动网络在特征代表方面的力量不如繁琐的网络。为此,我们认为,彩色图像的深度信息如果得到适当利用,可以加强与SOD有关的特征表现。因此,我们提议采用隐性深度恢复技术,以加强RGB-D显著物体探测(SOD)的移动网络特征表现能力。IDR只是在培训阶段才被采用,在测试期间被遗漏,因此在计算上是免费的。此外,我们提议对高效的多层次特征聚合进行紧凑(CPR),以获得清晰边界的突出物体。随着IRD和CPR的整合,MobSal在六种挑战RGB-D SOD数据集的州-艺术方法方面表现得较好。因此,我们提议以更快的速度(450fps)加强RGB-D SOD数据集的定位能力。在320美元/320的输入大小和低移动参数(6.M)释放。