Hierarchical Bayesian image analysis: From low-level modeling to robust supervised learning
作者：
Highlights：
• This paper proposes a unified framework to perform classification and low-level modeling jointly.
• Robustness is improved by considering a possibly badly labeled training set.
• The proposed model allows a very rich interpretation of the modeled data structure.
• Performance is assessed on synthetic and real data in the specific context of hyperspectral image interpretation.
• The proposed model is generic enough to incorporate any kind of low-level modeling.
摘要
•This paper proposes a unified framework to perform classification and low-level modeling jointly.•Robustness is improved by considering a possibly badly labeled training set.•The proposed model allows a very rich interpretation of the modeled data structure.•Performance is assessed on synthetic and real data in the specific context of hyperspectral image interpretation.•The proposed model is generic enough to incorporate any kind of low-level modeling.
论文关键词：Bayesian model,Supervised learning,Image interpretation,Markov random field
论文评审过程：Received 30 November 2017, Revised 11 May 2018, Accepted 22 July 2018, Available online 31 July 2018, Version of Record 8 August 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.07.026
