MobileSal: Extremely Efficient RGB-D Salient Object Detection

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 12; pp. 10261 - 10269
• Main Authors: Wu, Yu-Huan, Liu, Yun, Xu, Jun, Bian, Jia-Wang, Gu, Yu-Chao, Cheng, Ming-Ming
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Color imagery; Convolution; efficiency; Feature extraction; Fuses; Image restoration; implicit depth restoration; Neural networks; Object detection; Object recognition; Representations; RGB-D salient object detection; Salience; Semantics; Streaming media

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 article introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extrac...