• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Theory of operator manifold and its application to pattern recognition

Research Project

Project/Area Number 17H01760
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Perceptual information processing
Research InstitutionTokyo Institute of Technology

Principal Investigator

Yukihiko Yamashita  東京工業大学, 環境・社会理工学院, 准教授 (90220350)

Co-Investigator(Kenkyū-buntansha) 杉山 将  東京大学, 大学院新領域創成科学研究科, 教授 (90334515)
田中 聡久  東京農工大学, 工学(系)研究科(研究院), 教授 (70360584)
鷲沢 嘉一  電気通信大学, 大学院情報理工学研究科, 准教授 (10419880)
Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥17,940,000 (Direct Cost: ¥13,800,000、Indirect Cost: ¥4,140,000)
Fiscal Year 2019: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2018: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
Keywords作用素多様体 / 局所等方独立 / 機械学習 / 信号処理 / パターン認識 / ドメイン適応 / 正定値行列 / 相関行列
Outline of Final Research Achievements

In this research, as the basic part of the theory for operator manifolds, we defined the differentials for operators and an operation that corresponds to the differential of differentials contained in an operator. By using them, we provided an operator equation expressing the local isotropic independence. We also provided a solution for a simple case and an equation derived from the fact that the operator is space-invariant.
Furthermore, we have developed methods to obtain a curved coordinate system using local correlation given by the Mahalanobis metric defined by using the equation for the local isotropic independence, to obtain the deformation of an image by combining the canonical correlation and local features of images, to adapt to different domains in pattern recognition by using attributes of patterns, to detect outliers of EEG by using spectral distance as a Riemannian distance, and to smooth image using local statistical features of images.

Academic Significance and Societal Importance of the Research Achievements

パターン認識は知能の中では最も基本的なものの一つである。機械によるパターン認識の性能を向上させることができれば,人間が行ってきた単純作業や危険な作業を機械に肩代わりさせることができるため,人類の福祉向上に大きく貢献することができる。
パターン認識の分野では,深層学習が集中的に研究され,様々な分野にブレークスルーをもたらし,実応用に関しても広がりを見せている。しかし,残念がながら人間のパターン認識能力には遠く及ばない。この問題を解決するためには,パターンの距離構造や確率構造を含んだ生成モデルを構築することが重要であり,そのための上記の成果は独創性も非常に高く,学術的意義は大きいと言える。

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Annual Research Report
  • 2017 Annual Research Report
  • Research Products

    (20 results)

All 2020 2019 2018 2017

All Journal Article (17 results) (of which Int'l Joint Research: 3 results,  Peer Reviewed: 14 results,  Open Access: 5 results) Presentation (3 results)

  • [Journal Article] Anisotropic Guided Filtering2020

    • Author(s)
      Ochotorena Carlo Noel and Yukihiko Yamashita
    • Journal Title

      IEEE Transactions on Image Processing

      Volume: 29 Pages: 1397-1412

    • DOI

      10.1109/tip.2019.2941326

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Partially zero-shot domain adaptation from incomplete target data with missing classes2020

    • Author(s)
      Masato Ishii, Takeshi Takenouchi, and Masashi Sugiyama
    • Journal Title

      Proceedings of The IEEE Winter Conference on Applications of Computer Vision

      Volume: - Pages: 3052-3060

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Robust kernel principal component analysis with l2,1-regularized loss minimization2020

    • Author(s)
      Duo Wang and Toshihisa Tanaka
    • Journal Title

      IEEE Access

      Volume: -

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Detecting EEG outliers for BCI on the Riemannian manifold using spectral clustering2020

    • Author(s)
      Maria Sayu Yamamoto, Khadijeh Sadatnejad, Toshihisa Tanaka, Md. Rabiul Islam, Yuichi Tanaka, and Fabien Lotte
    • Journal Title

      2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

      Volume: -

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Image registration using 2D projection transformation invariant GPT correlation2019

    • Author(s)
      Toru Wakahara, Shizhi Zhang, Yukihiko Yamashita
    • Journal Title

      Proc. of 2019 International Workshop on Advanced Image Technology (IWAIT2019)

      Volume: 11049 Pages: 5-5

    • DOI

      10.1117/12.2517185

    • Related Report
      2019 Annual Research Report 2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Zero-shot domain adaptation based on attribute information2019

    • Author(s)
      Masato Ishii, Takeshi Takenouchi, and Masashi Sugiyama
    • Journal Title

      Proceedings of the 11th Asian Conference on Machine Learning

      Volume: - Pages: 473-488

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Kernel principal component analysis allowing sparse representation and sample selection2019

    • Author(s)
      Duo Wang and Toshihisa Tanaka
    • Journal Title

      ECTI Transactions on Computer and Information Technology

      Volume: 13 Pages: 51-62

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Spontaneous EEG Classification Using Complex Valued Neural Network2019

    • Author(s)
      Akira Ikeda and Yoshikazu Washizawa
    • Journal Title

      Proceedings of 26th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Society

      Volume: - Pages: 495-503

    • DOI

      10.1007/978-3-030-36808-1_54

    • ISBN
      9783030368074, 9783030368081
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Unsupervised domain adaptation based on source-guided discrepancy2019

    • Author(s)
      S. Kuroki, N. Charoenphakdee, H. Bao, J. Honda, I. Sato, and M. Sugiyama
    • Journal Title

      Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI2019)

      Volume: -

    • Related Report
      2018 Annual Research Report
  • [Journal Article] Multiband tangent space mapping and feature selection for classification of EEG during motor imagery2018

    • Author(s)
      Islam Md Rabiul、Tanaka Toshihisa、Molla Md Khademul Islam
    • Journal Title

      Journal of Neural Engineering

      Volume: 15 Issue: 4 Pages: 046021-046021

    • DOI

      10.1088/1741-2552/aac313

    • Related Report
      2018 Annual Research Report
  • [Journal Article] Discriminative sparse representation learning using multiclass hinge loss2018

    • Author(s)
      R. Kamiya and Y. Washizawa
    • Journal Title

      2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

      Volume: - Pages: 955-958

    • DOI

      10.23919/apsipa.2018.8659572

    • Related Report
      2018 Annual Research Report
  • [Journal Article] Dictonary learning for learning for Gaussian kernel adaptive filtering with variable kernel center and width2018

    • Author(s)
      T. Wada, K. Fukumori, and T. Tanaka
    • Journal Title

      Proceedings of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing

      Volume: 採録決定

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] EEG based automatic music recommendation system using ranking deep artificial neural network2018

    • Author(s)
      H. Itoga, Y. Washizawa, and Y. Urakami
    • Journal Title

      Proceedings of the 8th International Congress of Pathophysiology

      Volume: 採録決定

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Multi-scale structure-preserving image filtering2017

    • Author(s)
      Carlo Noel Ochotorena and Yukihiko Yamashita
    • Journal Title

      Proceedings of 2017 IEEE 19th International Workshop on Multimedia Signal Processing

      Volume: - Pages: 1-6

    • DOI

      10.1109/mmsp.2017.8122290

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Image Matching Using GPT Correlation Associated with Simplified HOG Patterns2017

    • Author(s)
      Shizhi Zhang, Toru Wakahara, Yukihiko Yamashita
    • Journal Title

      Proc. of 7th International Conference on Image Processing Theory, Tools and Applications

      Volume: 1 Pages: 1-6

    • DOI

      10.1109/ipta.2017.8310122

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Generative local metric learning for kernel regression2017

    • Author(s)
      Y.-K. Noh, M. Sugiyama, K.-Y., Kim, F. C. Park, and D. D. Lee
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 30 Pages: 2449-2459

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Learning discrete representations via information maximizing self-augmented training2017

    • Author(s)
      W. Hu, T. Miyato, S. Tokui, E. Matsumoto, and M. Sugiyama
    • Journal Title

      Proceedings of 34th International Conference on Machine Learning

      Volume: 70 Pages: 1558-1567

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] Wavelet Based Image Coding via Image Component Prediction using Neural Networks2020

    • Author(s)
      Takuma Takezawa and Yukihiko Yamashita
    • Organizer
      2019 5th International Conference on Signal Processing
    • Related Report
      2019 Annual Research Report
  • [Presentation] 領域画像マッチングのための初期探索法2018

    • Author(s)
      山下幸彦, 若原徹
    • Organizer
      パターン認識・メディア理解研究会 (PRMU)
    • Related Report
      2018 Annual Research Report
  • [Presentation] IIRフィルタを使った画像の近似ガウス平滑化2018

    • Author(s)
      山下幸彦
    • Organizer
      2018年電子情報通信学会総合大会
    • Related Report
      2017 Annual Research Report

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi