MobileSal: Extremely Efficient RGB-D Salient Object Detection
This work provides a more efficient solution for real-world applications requiring RGB-D salient object detection, particularly for scenarios with computational constraints.
This paper addresses the high computational cost of RGB-D salient object detection (SOD) by introducing MobileSal, a novel network that achieves state-of-the-art performance with significantly higher speed (450fps) and fewer parameters (6.5M) on six RGB-D SOD datasets. The network leverages an implicit depth restoration (IDR) technique during training and a compact pyramid refinement (CPR) for efficient multi-level feature aggregation.
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.