LZY 李 宗曜

  • TOP
  • 李 宗曜

李 宗曜 Zongyao Li

領域分割・物体検出におけるドメイン適応に加え，機械学習技術を応用した医用画像解析に関する研究に従事．
IEEE，電子情報通信学会 会員．
Google Scholar

学歴

  • 2023年10月-現在 NEC 研究員
  • 2021年4月-2023年9月 日本学術振興会 特別研究員DC1
  • 2020年10月-2023年9月 北海道大学大学院情報科学院 博士課程
  • 2018年10月-2020年9月 北海道大学大学院情報科学院 修士課程
  • 2018年4月-2018年9月 北海道大学大学院情報科学院 研究生
  • 2012年9月-2016年6月 浙江大学 航空航天学院

研究業績

論文誌

  • Zongyao Li, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Generalizing deep learning-based distress segmentation models for subway tunnel images by test-time training,” Intelligence, Informatics and Infrastructure, 2024.
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Source-data-free cross-domain knowledge transfer for semantic segmentation,” IEEE Open Journal of Signal Processing, vol. 5, pp. 92-100, 2024. [Paper]
  • Zongyao Li, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Developing technologies for the practical application of deep learning-based distress segmentation in subway tunnel images,” Intelligence, Informatics and Infrastructure, vol. 4, no. 1, pp. 1-8, 2023. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Learning intra-domain style-invariant representation for unsupervised domain adaptation of semantic segmentation,” Pattern Recognition, vol. 132, 108911, 2022. [Paper]
  • Zongyao Li, Kazuhiro Kitajima, Kenji Hirata, Ren Togo, Junki Takenaka, Yasuo Miyoshi, Kohsuke Kudo, Takahiro Ogawa, Miki Haseyama, “Preliminary study of AI-assisted diagnosis using FDG-PET/CT for axillary lymph node metastasis in patients with breast cancer,” EJNMMI Research, vol. 11, no. 1, pp. 1-10, 2021. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Chronic gastritis classification using gastric X-ray images with a semi-supervised learning method based on tri-training,” Medical & Biological Engineering & Computing, vol. 58, pp. 1239-1250, 2020. [Paper]
  • Hongsheng Jin, Zongyao Li, Ruofeng Tong, Lanfen Lin, “A deep 3D residual CNN for false‐positive reduction in pulmonary nodule detection,” Medical Physics, vol. 45, no. 5, pp. 2097-2107, 2018. [Paper]

国際会議

  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Source-data-free cross-domain knowledge transfer for semantic segmentation,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Korea, 2024. [Paper] (OJSP Track)
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Union-set multi-source model adaptation for semantic segmentation,” European Conference on Computer Vision (ECCV), pp. 579-595, Virtual, 2022. [Code] [arXiv] [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Improving model adaptation for semantic segmentation by learning model-invariant features with multiple source-domain models,” IEEE International Conference on Image Processing (ICIP), pp. 421-425, Virtual, 2022. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama: “Divergence-guided feature alignment for cross-domain object detection,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2240-2244, Virtual, 2022. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama: “Semantic-aware unpaired image-to-image translation for urban scene images,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 2150-2154, Virtual, 2021. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Variational autoencoder based unsupervised domain adaptation for semantic segmentation,” IEEE International Conference on Image Processing (ICIP), pp. 2426-2430, Virtual, 2020. [Paper]
  • Zongyao Li,  Ren Togo, Takahiro Ogawa, Miki Haseyama, “Unsupervised domain adaptation for semantic segmentation with symmetric adaptation consistency,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Classification of subcellular protein patterns in human cells with transfer learning,” IEEE Global Conference on Life Sciences and Technologies (LifeTech), pp. 273-274, Osaka, Japan, 2019. [Paper]
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Semi-supervised learning based on tri-training for gastritis classification using gastric X-ray images,” IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, Sapporo, Japan, 2019. [Paper]

国内会議

  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Source-data-free Domain-adaptive Semantic Segmentation with Inter-domain and Intra-domain Style Transfer,” 画像の認識・理解シンポジウム (MIRU), 浜松, 2023.
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Union-set model adaptation for semantic segmentation using multiple source domains with subset label spaces,” 画像の認識・理解シンポジウム (MIRU), 姫路, 2022.
  • 李 宗曜, 藤後 廉, 小川 貴弘, 長谷山 美紀, “セマンティックセグメンテーションに対するマルチソースモデル適応に関する検討 ～ 複数のソースモデルからの不変な特徴表現の学習による適応精度の向上 ～” 映像情報メディア学会技術報告, vol. 46, no. 6, pp. 37-41, オンライン, 2022.
  • Zongyao Li, Ren Togo, Kenji Hirata, Kazuhiro Kitajima, Junki Takenaka, Yasuo Miyoshi, Kohsuke Kudo, Takahiro Ogawa, Miki Haseyama, “Detecting axillary lymph node metastasis of breast cancer with FDG-PET/CT images based on attention mechanism,” 映像情報メディア学会技術報告, vol. 45, no. 4, pp. 33-36, オンライン, 2021.
  • Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “A note on retrieval of visually similar distress regions in subway tunnel images -Introduction of deep features extracted by semantic segmentation network-,” 映像情報メディア学会技術報告, vol. 44, no. 6, pp. 65-68, 札幌, 2020.
  • 李 宗曜, 藤後 廉, 小川 貴弘, 平田 健司, 真鍋 治, 志賀 哲, 長谷山 美紀, “3D residual networkに基づくFDG-PET/CT画像を用いた悪性腫瘍候補の自動検出,” 映像情報メディア学会技術報告, vol. 43, no. 5, pp. 311-314, 札幌, 2019.
  • 李 宗曜, 藤後 廉, 小川 貴弘, 長谷山 美紀, “Tri-trainingに基づく胃X線画像を用いた胃炎の識別に関する検討,” 電気・情報関係学会北海道支部連合大会 講演論文集, 札幌, pp. 130-131, 2018.

受賞等

  • MIRU学生奨励賞
  • 日本学術振興会 特別研究員DC1
  • 北海道大学大学院情報科学院 研究院長賞