Masaki Saito


PhD Candidate
Department of Information Sciences, Tohoku University
6-6-01 Aza Aoba, Aramaki, Aoba-ku, Sendai, Japan

Phone: (+81)22-374-3627

Advisor: Prof. Takayuki Okatani
Research interests: Markov random fields, Belief propagation, Mean field inference, TAP equation


  • PhD, Information Science, Tohoku University (April 2013 - present)
    • Advisor: Takayuki Okatani
  • MS, Information Science, Tohoku Univeristy (April 2011 - March 2013)
    • Advisor: Takayuki Okatani, Koichiro Deguchi
  • BS, Department of Physics, Tohoku University (April 2007 - March 2011)
    • Advisor: Yasuhiro Sakemi

Recent research

Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space

Masaki Saito, Takayuki Okatani, Koichiro Deguchi. CVPR, 2013. [PDF][supplementary material][poster]

This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is quite common to convert the continuous variables into discrete ones for the problems that ideally should be solved in the continuous domain, such as stereo matching and optical flow estimation. In this paper, we show a novel formulation for this continuous-discrete conversion. The key idea is to estimate the marginal densities in the continuous domain by approximating them with mixtures of rectangular densities. Based on this formulation, we derive a mean field (MF) algorithm and a belief propagation (BP) algorithm. These algorithms can correctly handle the case where the variable space is discretized in a non-uniform manner. By intentionally using such a non-uniform discretization, a higher balance between computational efficiency and accuracy of marginal density estimates could be achieved. We present a method for actually doing this, which dynamically discretizes the variable space in a coarse-to-fine manner in the course of the computation. Experimental results show the effectiveness of our approach.

Application of the Mean Field Methods to MRF Optimization in Computer Vision

Masaki Saito, Takayuki Okatani, Koichiro Deguchi. CVPR, 2012. [PDF]

The mean field (MF) methods are an energy optimization method for Markov random fields (MRFs). These methods, which have their root in solid state physics, estimate the marginal density of each site of an MRF graph by iterative computation, similarly to loopy belief propagation (LBP). It appears that, being shadowed by LBP, the MF methods have not been seriously considered in the computer vision community. This study investigates whether these methods are useful for practical problems, particularly MPM (Maximum Posterior Marginal) inference, in computer vision. To be specific, we apply the naive MF equations and the TAP (Thouless-Anderson-Palmer) equations to interactive segmentation and stereo matching. In this paper, firstly, we show implementation of these methods for computer vision problems. Next, we discuss advantages of the MF methods to LBP. Finally, we present experimental results that the MF methods are well comparable to LBP in terms of accuracy and global convergence; furthermore, the 3rd-order TAP equation often outperforms LBP in terms of accuracy.


International Conference

  • Masaki Saito, Yusuke Matsui, "Illustration2Vec: A Semantic Vector Representation of Illustrations", In Proceedings of the ACM SIGGRAPH Asia Technical Brief, Kobe, Japan, November, 2015 [Project Page]
  • Masaki Saito, Takayuki Okatani, "Transformation of Markov Random Fields for Marginal Distribution Estimation", In Proceedings of the Computer Vision and Pattern Recognition(CVPR 2015), Boston, USA, June, 2015 [PDF][extended abstract] (acceptance rate: 602/2123 = 28%)
  • Masaki Saito, Takayuki Okatani, Koichiro Deguchi, "Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space", In Proceedings of the Computer Vision and Pattern Recognition(CVPR 2013), Oregon, USA, June, 2013. [PDF][supplementary material][poster] (oral acceptance rate: 60/1870 = 3.2%)
  • Masaki Saito, Takayuki Okatani, Koichiro Deguchi, "Application of the Mean Field Methods to MRF Optimization in Computer Vision", In Proceedings of the Computer Vision and Pattern Recognition(CVPR 2012), Rhode Island, USA, June, 2012. [PDF] (acceptance rate: 465/1933 = 24%)

Domestic Conference (Peer Review)

  • 齋藤真樹,岡谷貴之,出口光一郎,”コンピュータビジョンにおけるMRF最適化問題への平均場近似及びその拡張手法の応用”,画像の認識・理解シンポジウム(MIRU 2012),福岡,2012年8月.
    (口頭発表採択率: 37%)
  • Sumit Maharjan, Masaki Saito, Kota Yamaguchi, Naoaki Okazaki, Takayuki Okatani, Kentaro Inui, "Learning Visual Attributes from Image and Text", 言語処理学会 第21回年次大会, 京都, 2015年3月

Domestic Conference (without Peer Review)

  • 岡谷貴之齋藤真樹,”ディープラーニング”,コンピュータビジョンとイメージメディア研究会(CVIM 2013)チュートリアルセッション,京都,2013年1月


  • Master Thesis, "A Study of the Mean Field Approximation and its Extension Methods for Markov Random Field Optimization in Computer Vision", March, 2013. (Japanese) [PDF]