Adaptive fusion network for RGB-D salient object detection

被引:15
|
作者
Chen, Tianyou [1 ]
Xiao, Jin [1 ]
Hu, Xiaoguang [1 ]
Zhang, Guofeng [1 ]
Wang, Shaojie [1 ]
机构
[1] Beihang Univ, 37 Xueyuan Rd, Beijing 100191, Peoples R China
关键词
RGB-D salient object detection; Multi-modality feature interaction; Adaptive fusion; Deep learning;
D O I
10.1016/j.neucom.2022.12.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing state-of-the-art RGB-D saliency detection models mainly utilize the depth information as com-plementary cues to enhance the RGB information. However, depth maps can be easily influenced by envi-ronment and hence are full of noises. Thus, indiscriminately integrating multi-modality (i.e., RGB and depth) features may induce noise-degraded saliency maps. In this paper, we propose a novel Adaptive Fusion Network (AFNet) to solve this problem. Specifically, we design a triplet encoder network consist-ing of three subnetworks to process RGB, depth, and fused features, respectively. The three subnetworks are interlinked and form a grid net to facilitate mutual refinement of these multi-modality features. Moreover, we propose a Multi-modality Feature Interaction (MFI) module to exploit complementary cues between depth and RGB modalities and adaptively fuse the multi-modality features. Finally, we design the Cascaded Feature Interweaved Decoder (CFID) to exploit complementary information between multi-level features and refine them iteratively to achieve accurate saliency detection. Experimental results on six commonly used benchmark datasets verify that the proposed AFNet outperforms 20 state-of-the-art counterparts in terms of six widely adopted evaluation metrics. Source code will be pub-licly available athttps://github.com/clelouch/AFNet upon paper acceptance. (c) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页码:152 / 164
页数:13
相关论文
共 50 条
  • [1] An adaptive guidance fusion network for RGB-D salient object detection
    Sun, Haodong
    Wang, Yu
    Ma, Xinpeng
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (02) : 1683 - 1693
  • [2] Scale Adaptive Fusion Network for RGB-D Salient Object Detection
    Kong, Yuqiu
    Zheng, Yushuo
    Yao, Cuili
    Liu, Yang
    Wang, He
    [J]. COMPUTER VISION - ACCV 2022, PT III, 2023, 13843 : 608 - 625
  • [3] An adaptive guidance fusion network for RGB-D salient object detection
    Haodong Sun
    Yu Wang
    Xinpeng Ma
    [J]. Signal, Image and Video Processing, 2024, 18 : 1683 - 1693
  • [4] Adaptive Fusion for RGB-D Salient Object Detection
    Wang, Ningning
    Gong, Xiaojin
    [J]. IEEE ACCESS, 2019, 7 : 55277 - 55284
  • [5] Bifurcation Fusion Network for RGB-D Salient Object Detection
    Zhao, Zhi-Hua
    Chen, Li
    [J]. JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2022, 31 (12)
  • [6] Heterogeneous Fusion and Integrity Learning Network for RGB-D Salient Object Detection
    Gao, Haorao
    Su, Yiming
    Wang, Fasheng
    Li, Haojie
    [J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 20 (07)
  • [7] Discriminative feature fusion for RGB-D salient object detection
    Chen, Zeyu
    Zhu, Mingyu
    Chen, Shuhan
    Lu, Lu
    Tang, Haonan
    Hu, Xuelong
    Ji, Chunfan
    [J]. COMPUTERS & ELECTRICAL ENGINEERING, 2023, 106
  • [8] Progressively Complementarity-aware Fusion Network for RGB-D Salient Object Detection
    Chen, Hao
    Li, Youfu
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3051 - 3060
  • [9] Progressive multi-scale fusion network for RGB-D salient object detection
    Ren, Guangyu
    Xie, Yanchun
    Dai, Tianhong
    Stathaki, Tania
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2022, 223
  • [10] Boosting RGB-D salient object detection with adaptively cooperative dynamic fusion network
    Zhu, Jinchao
    Zhang, Xiaoyu
    Fang, Xian
    Rahman, Muhammad Rameez Ur
    Dong, Feng
    Li, Yuehua
    Yan, Siyu
    Tan, Panlong
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 251