Efficient Salient Object Detection
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 efficient SOD by designing lightweight CNNs. Our two papers have been published on IEEE TIP and IEEE TCYB. In these papers, our methods achieve competitive performance with extremely high speed when compared to traditional cumbersome methods. Please see the papers for more details!
Papers
- SAMNet: Stereoscopically Attentive Multi-scale Network for Lightweight Salient Object Detection, Yun Liu#, Xin-Yu Zhang#, Jia-Wang Bian, Le Zhang, Ming-Ming Cheng*, IEEE TIP, 2021. [pdf | project | code]
- Lightweight Salient Object Detection via Hierarchical Visual Perception Learning, Yun Liu#, Yu-Chao Gu#, Xin-Yu Zhang#, Weiwei Wang, Ming-Ming Cheng*, IEEE T Cybernetics, 2020. [pdf | code | bib ]
Recently, we propose a very efficient RGB-D SOD method called MobileSal. You can click project for more details.
- MobileSal: Extremely Efficient RGB-D Salient Object Detection, Yu-Huan Wu, Yun Liu, Jun Xu, Jia-Wang Bian, Yu-Chao Gu, Ming-Ming Cheng*, IEEE TPAMI, 2021. [pdf | bib | code | project | 中译版]
Note: We release the precomputed saliency maps of 12 popular datasets for comparison here.
