A novel deep network and aggregation model for saliency detection

被引:4
作者
Liang, Ye [1 ]
Liu, Hongzhe [1 ]
Ma, Nan [2 ]
机构
[1] Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing, Peoples R China
[2] Beijing Union Univ, Coll Robot, Beijing, Peoples R China
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
Saliency detection; Multi-scale network; Feature pyramid; Saliency aggregation; OBJECT DETECTION; CONTRAST;
D O I
10.1007/s00371-019-01781-9
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Recent deep learning-based methods for saliency detection have proved the effectiveness of integrating features with different scales. They usually design various complex architectures of network, e.g., multiple networks, to explore the multi-scale information of images, which is expensive in computation and memory. Feature maps produced with different subsampling convolutional layers have different spatial resolutions; therefore, they can be used as the multi-scale features to reduce the costs. In this paper, by exploiting the in-network feature hierarchy of convolutional networks, we propose a novel multi-scale network for saliency detection (MSNSD) consisting of three modules, i.e., bottom-up feature extraction, top-down feature connection and multi-scale saliency prediction. Moreover, to further boost the performance of MSNSD, an input image-aware saliency aggregation method is proposed based on the ridge regression, which combines MSNSD with some well-performed handcrafted shallow models. Extensive experiments on several benchmarks show that the proposed MSNSD outperforms the state-of-the-art saliency methods with less computational and memory complexity. Meanwhile, our aggregation method for saliency detection is effective and efficient to combine deep and shallow models and make them complementary to each other.
引用
收藏
页码:1883 / 1895
页数:13
相关论文
共 74 条
[1]  
Achanta R, 2009, PROC CVPR IEEE, P1597, DOI 10.1109/CVPRW.2009.5206596
[2]  
[Anonymous], 2019, ARXIV190310152
[3]  
[Anonymous], 2018, 2018 IEEE 23 INT C D
[4]  
[Anonymous], 2016, ARXIV161203144 CORR
[5]   Salient Object Detection: A Benchmark [J].
Borji, Ali ;
Sihite, Dicky N. ;
Itti, Laurent .
COMPUTER VISION - ECCV 2012, PT II, 2012, 7573 :414-429
[6]   Reverse Attention for Salient Object Detection [J].
Chen, Shuhan ;
Tan, Xiuli ;
Wang, Ben ;
Hu, Xuelong .
COMPUTER VISION - ECCV 2018, PT IX, 2018, 11213 :236-252
[7]   Look, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs [J].
Chen, Xiaowu ;
Zheng, Anlin ;
Li, Jia ;
Lu, Feng .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :1050-1058
[8]   Intelligent Visual Media Processing: When Graphics Meets Vision [J].
Cheng, Ming-Ming ;
Hou, Qi-Bin ;
Zhang, Song-Hai ;
Rosin, Paul L. .
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2017, 32 (01) :110-121
[9]   RepFinder: Finding Approximately Repeated Scene Elements for Image Editing [J].
Cheng, Ming-Ming ;
Zhang, Fang-Lue ;
Mitra, Niloy J. ;
Huang, Xiaolei ;
Hu, Shi-Min .
ACM TRANSACTIONS ON GRAPHICS, 2010, 29 (04)
[10]   Global Contrast based Salient Region Detection [J].
Cheng, Ming-Ming ;
Zhang, Guo-Xin ;
Mitra, Niloy J. ;
Huang, Xiaolei ;
Hu, Shi-Min .
2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, :409-416