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

Page view(s)
79
Checked on Jan 13, 2025
SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection
Title:
SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection
Journal Title:
IEEE Transactions on Image Processing
Publication Date:
18 March 2021
Citation:
Liu, Y., Zhang, X.-Y., Bian, J.-W., Zhang, L., & Cheng, M.-M. (2021). SAMNet: Stereoscopically Attentive Multi-Scale Network for Lightweight Salient Object Detection. IEEE Transactions on Image Processing, 30, 3804–3814. https://doi.org/10.1109/tip.2021.3065239
Abstract:
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 ×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/.
License type:
Publisher Copyright
Funding Info:
This research was supported by Major Project for New Generation of AI under Grant No. 2018AAA0100400, NSFC (61922046), S&T innovation project from Chinese Ministry of Education, and Tianjin Natural Science Foundation (17JCJQJC43700).
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1941-0042
1057-7149
Files uploaded:

File Size Format Action
20tip-samnetextremfastsal-1.pdf 1.75 MB PDF Open