Cross-Modal Weighting Network for RGB-D Salient Object Detection

被引:153
作者
Li, Gongyang [1 ]
Liu, Zhi [1 ]
Ye, Linwei [2 ]
Wang, Yang [2 ,4 ]
Ling, Haibin [3 ]
机构
[1] Shanghai Univ, Shanghai, Peoples R China
[2] Univ Manitoba, Winnipeg, MB, Canada
[3] SUNY Stony Brook, Stony Brook, NY USA
[4] Huawei Technol Canada, Markham, ON, Canada
来源
COMPUTER VISION - ECCV 2020, PT XVII | 2020年 / 12362卷
基金
加拿大自然科学与工程研究理事会; 中国国家自然科学基金;
关键词
RGB-D salient object detection; Cross-Modal Weighting; Depth-to-RGB weighting; RGB-to-RGB weighting; FUSION; ATTENTION;
D O I
10.1007/978-3-030-58520-4_39
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Depth maps contain geometric clues for assisting Salient Object Detection (SOD). In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD. Specifically, three RGB-depth interaction modules, named CMW-L, CMW-M and CMW-H, are developed to deal with respectively low-, middle- and high-level cross-modal information fusion. These modules use Depth-to-RGB Weighing (DW) and RGB-to-RGB Weighting (RW) to allow rich cross-modal and cross-scale interactions among feature layers generated by different network blocks. To effectively train the proposed Cross-Modal Weighting Network (CMWNet), we design a composite loss function that summarizes the errors between intermediate predictions and ground truth over different scales. With all these novel components working together, CMWNet effectively fuses information from RGB and depth channels, and meanwhile explores object localization and details across scales. Thorough evaluations demonstrate CMWNet consistently outperforms 15 state-of-the-art RGB-D SOD methods on seven popular benchmarks.
引用
收藏
页码:665 / 681
页数:17
相关论文
共 45 条
[1]   Salient Object Detection: A Benchmark [J].
Borji, Ali ;
Cheng, Ming-Ming ;
Jiang, Huaizu ;
Li, Jia .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (12) :5706-5722
[2]   Salient object detection: A survey [J].
Borji, Ali ;
Cheng, Ming-Ming ;
Hou, Qibin ;
Jiang, Huaizu ;
Li, Jia .
COMPUTATIONAL VISUAL MEDIA, 2019, 5 (02) :117-150
[3]   Large-Scale Machine Learning with Stochastic Gradient Descent [J].
Bottou, Leon .
COMPSTAT'2010: 19TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STATISTICS, 2010, :177-186
[4]   Three-Stream Attention-Aware Network for RGB-D Salient Object Detection [J].
Chen, Hao ;
Li, Youfu .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (06) :2825-2835
[5]   Progressively Complementarity-aware Fusion Network for RGB-D Salient Object Detection [J].
Chen, Hao ;
Li, Youfu .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :3051-3060
[6]   Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection [J].
Chen, Hao ;
Li, Youfu ;
Su, Dan .
PATTERN RECOGNITION, 2019, 86 :376-385
[7]  
Cheng Y., 2014, ACM ICIMCS
[8]   Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion [J].
Cong, Runmin ;
Lei, Jianjun ;
Zhang, Changqing ;
Huang, Qingming ;
Cao, Xiaochun ;
Hou, Chunping .
IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (06) :819-823
[9]   Going From RGB to RGBD Saliency: A Depth-Guided Transformation Model [J].
Cong, Runmin ;
Lei, Jianjun ;
Fu, Huazhu ;
Hou, Junhui ;
Huang, Qingming ;
Kwong, Sam .
IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (08) :3627-3639
[10]   Depth-aware saliency detection using convolutional neural networks [J].
Ding, Yu ;
Liu, Zhi ;
Huang, Mengke ;
Shi, Ran ;
Wang, Xiangyang .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 61 :1-9