LEARNING FULL-RANGE AFFINITY FOR DIFFUSION-BASED SALIENCY DETECTION

被引:0
|
作者
Fu, Keren [1 ,2 ]
Gu, Irene Y. H. [1 ]
Yang, Jie [2 ]
机构
[1] Chalmers Univ Technol, Dept Signals & Syst, Gothenburg, Sweden
[2] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai, Peoples R China
关键词
Saliency detection; graph-based diffusion; affinity learning; semi-supervised learning;
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
In this paper we address the issue of enhancing salient object detection through diffusion-based techniques. For reliably diffusing the energy from labeled seeds, we propose a novel graph-based diffusion scheme called affinity learning-based diffusion (ALD), which is based on learning full-range affinity between two arbitrary graph nodes. The method differs from the previous existing work where implicit diffusion was formulated as a ranking problem on a graph. In the proposed method, the affinity learning is achieved in a unified graph-based semi-supervised manner, whose outcome is leveraged for global propagation. By properly selecting an affinity learning model, the proposed ALD outperforms the ranking-based diffusion in terms of accurately detecting salient objects and enhancing the correct salient objects under a range of background scenarios. By utilizing the ALD, we propose an enhanced saliency detector that outperforms 7 recent state-of-the-art saliency models on 3 benchmark datasets.
引用
收藏
页码:1926 / 1930
页数:5
相关论文
共 50 条
  • [41] Generic Promotion of Diffusion-Based Salient Object Detection
    Jiang, Peng
    Vasconcelos, Nuno
    Peng, Jingliang
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 217 - 225
  • [42] Iterative Signal Detection for Diffusion-Based Molecular Communications
    Thakur, Mahendra S.
    Sharma, Sanjeev
    Bhatia, Vimal
    IEEE TRANSACTIONS ON MOLECULAR BIOLOGICAL AND MULTI-SCALE COMMUNICATIONS, 2020, 6 (01): : 36 - 49
  • [43] Saliency detection via affinity graph learning and weighted manifold ranking
    Zhu, Xinzhong
    Tang, Chang
    Wang, Pichao
    Xu, Huiying
    Wang, Minhui
    Chen, Jiajia
    Tian, Jie
    NEUROCOMPUTING, 2018, 312 : 239 - 250
  • [44] Full-range adaptive cruise control based on supervised adaptive dynamic programming
    Zhao, Dongbin
    Hu, Zhaohui
    Xia, Zhongpu
    Alippi, Cesare
    Zhu, Yuanheng
    Wang, Ding
    NEUROCOMPUTING, 2014, 125 : 57 - 67
  • [45] Study on the stress triaxiality of ductile materials based on the full-range constitutive relationship
    Qi, Shuang
    Cai, Li-Xun
    Bao, Chen
    Yao, Di
    Gongcheng Lixue/Engineering Mechanics, 2015, 32 : 27 - 32
  • [46] Full-range acoustic modulator based on magnetically-driven phononic crystal
    Khanshan, Zahra Seyedzadeh
    Bahrami, Ali
    Motaei, Farzaneh
    PHYSICA SCRIPTA, 2025, 100 (05)
  • [47] Saliency Detection via A Graph Based Diffusion Model
    He, Zhouqin
    Jiang, Bo
    Xiao, Yun
    Ding, Chris
    Luo, Bin
    GRAPH-BASED REPRESENTATIONS IN PATTERN RECOGNITION (GBRPR 2017), 2017, 10310 : 3 - 12
  • [48] The Crack Diffusion Model: An Innovative Diffusion-Based Method for Pavement Crack Detection
    Zhang, Haoyuan
    Chen, Ning
    Li, Mei
    Mao, Shanjun
    REMOTE SENSING, 2024, 16 (06)
  • [49] Bagging-based saliency distribution learning for visual saliency detection
    Pang, Yu
    Yu, Xiaosheng
    Wu, Yunhe
    Wu, Chengdong
    Jiang, Yang
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2020, 87
  • [50] Diffusion-based Multi-agent Reinforcement Learning with Communication
    Qi, Xinyue
    Tang, Jianhang
    Jin, Jiangming
    Zhang, Yang
    2024 IEEE VTS ASIA PACIFIC WIRELESS COMMUNICATIONS SYMPOSIUM, APWCS 2024, 2024,