SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection

• Published in: IEEE transactions on image processing 2021, Vol.30, p.3804-3814
• Main Authors: Liu, Yun, Zhang, Xin-Yu, Bian, Jia-Wang, Zhang, Le, Cheng, Ming-Ming
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Deep learning; Explosives detection; Fuses; Lightweight; lightweight saliency detection; Lightweight salient object detection; Modules; multi-scale learning; Object detection; Object recognition; Salience; Semantics; Source code; Stereo image processing; Task analysis; Visualization
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2021.3065239

Recent progress on salient object detection (SOD) mostly benefits from the explosive development of Convolutional Neural Networks (CNNs). However, much of the improvement comes with the larger network size and heavier computation overhead, which, in our view, is not mobile-friendly and thus difficult to deploy in practice. To promote more practical SOD systems, we introduce a novel Stereoscopically Attentive Multi-scale (SAM) module, which adopts a stereoscopic attention mechanism to adaptively fuse the features of various scales. Embarking on this module, we propose an extremely lightweight network, namely SAMNet, for SOD. Extensive experiments on popular benchmarks demonstrate that the proposed SAMNet yields comparable accuracy with state-of-the-art methods while running at a GPU speed of 343fps and a CPU speed of 5fps for 336 \times 336 inputs with only 1.33M parameters. Therefore, SAMNet paves a new path towards SOD. The source code is available on the project page https://mmcheng.net/SAMNet/ .