Details of the Researcher

PHOTO

Yusuke Hosoya
Section
Graduate School of Information Sciences
Job title
Assistant Professor
Degree

  • Doctor of Philosophy (Ph.D.) in Information Science

Research History 2

  • 2025/04 - Present
    Tohoku University　Graduate School of Information Sciences　Assistant Professor

  • 2022/04 - 2025/03
    Tohoku University　Graduate School of Information Sciences　PhD

Research Interests 3

  • 画像理解

  • 画像認識

  • Computer vision

Research Areas 1

  • Informatics / Intelligent robotics /

Awards 2

  1. MIRU2019

    2019/08

  2. 工学部長賞

    2019/03　東北大学

Papers 3

  1. Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy Peer-reviewed

    Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani

    International Journal of Computer Vision (IJCV)　2025/05/26

    Publisher: Springer Science and Business Media LLC

    DOI： 10.1007/s11263-025-02479-3 　

    ISSN： 0920-5691

    eISSN： 1573-1405

    More details Close

    Abstract Open-set object detection (OSOD), a task involving the detection of unknown objects while accurately detecting known objects, has recently gained attention. However, we identify a fundamental issue with the problem formulation employed in current OSOD studies. Inherent to object detection is knowing “what to detect,” which contradicts the idea of identifying “unknown” objects. This sets OSOD apart from open-set recognition (OSR). This contradiction complicates a proper evaluation of methods’ performance, a fact that previous studies have overlooked. Next, we propose a novel formulation wherein detectors are required to detect both known and unknown classes within specified super-classes of object classes. This new formulation is free from the aforementioned issues and has practical applications. Finally, we design benchmark tests utilizing existing datasets and report the experimental evaluation of existing OSOD methods. The results show that existing methods fail to accurately detect unknown objects due to misclassification of known and unknown classes rather than incorrect bounding box prediction. As a byproduct, we introduce a taxonomy of OSOD, resolving confusion prevalent in the literature. We anticipate that our study will encourage the research community to reconsider OSOD and facilitate progress in the right direction.

  2. Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors. Peer-reviewed

    Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani

    IEEE Winter Conference on Applications of Computer Vision(WACV)　1399-1407　2020

    Publisher: IEEE

    DOI： 10.1109/WACV45572.2020.9093553 　

  3. SSDを用いた画像中の移動物体検出の頑健性の評価 Peer-reviewed

    細矢 悠介, 岡谷 貴之

    第22回 画像の認識・理解シンポジウム (MIRU2019)　2019/07

Misc. 2

  1. MLLMはどのように文字を読むのか：最新モデルの比較

    酒井紘佑, 細矢悠介, 岡谷貴之

    第28回 画像の認識・理解シンポジウム（MIRU2025​）　2025/08

  2. 大規模言語モデルを用いたプログラム自動生成による論理的異常の画像検知

    鶴巻敬大, 細矢悠介, 岡谷貴之

    第28回 画像の認識・理解シンポジウム（MIRU2025​）　2025/08