Bifurcated Backbone Strategy for RGB-D Salient Object Detection
文献类型：期刊论文
| 作者 | Zhai, Yingjie5; Fan, Deng-Ping5; Yang, Jufeng5; Borji, Ali1; Shao, Ling4; Han, Junwei3; Wang, Liang2
|
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2021 |
| 卷号 | 30页码:8727-8742 |
| 关键词 | RGB-D salient object detection bifurcated backbone strategy multi-level features cascaded refinement |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2021.3116793 |
| 通讯作者 | Yang, Jufeng() |
| 英文摘要 | Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel Bifurcated Backbone Strategy Network (BBS-Net). Our architecture, is simple, efficient, and backbone-independent. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Extensive experiments show that BBS-Net significantly outperforms 18 state-of-the-art (SOTA) models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach (similar to 4% improvement in S-measure vs. the top-ranked model: DMRA). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research. The complete algorithm, benchmark results, and post-processing toolbox are publicly available at https://github.com/zyjwuyan/BBS-Net. |
| WOS关键词 | REGION DETECTION ; FUSION ; CONTRAST ; NETWORK ; IMAGE ; MODEL |
| 资助项目 | National Key Research and Development Program of China[2018AAA0100403] ; NSFC[61876094] ; NSFC[U1933114] ; Natural Science Foundation of Tianjin, China[20JCJQJC00020] ; Natural Science Foundation of Tianjin, China[18JCYBJC15400] ; Natural Science Foundation of Tianjin, China[18ZXZNGX00110] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000711755100006 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; NSFC ; Natural Science Foundation of Tianjin, China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/46276]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Yang, Jufeng |
| 作者单位 | 1.Primer Technol Inc, San Francisco, CA 94111 USA 2.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China 4.Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates 5.Nankai Univ, Coll Comp Sci, Tianjin 300350, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhai, Yingjie,Fan, Deng-Ping,Yang, Jufeng,et al. Bifurcated Backbone Strategy for RGB-D Salient Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:8727-8742. |
| APA | Zhai, Yingjie.,Fan, Deng-Ping.,Yang, Jufeng.,Borji, Ali.,Shao, Ling.,...&Wang, Liang.(2021).Bifurcated Backbone Strategy for RGB-D Salient Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,8727-8742. |
| MLA | Zhai, Yingjie,et al."Bifurcated Backbone Strategy for RGB-D Salient Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):8727-8742. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。