GUANG LI Guang Li

Short Bio: Guang Li is a Faculty Member of the Laboratory of Media Dynamics (LMD), a Specially Appointed Assistant Professor of the Education and Research Center for Mathematical and Data Science (MDS), and a Researcher of the Data-Driven Interdisciplinary Research Emergence Department (D-RED), at Hokkaido University. He earned his B.S. degree in Software Engineering and B.A. dual degree in Japanese from Dalian University of Technology, China, in 2019, and his M.S. and Ph.D. degrees in Information Science from Hokkaido University, Japan, in 2022 and 2023, advised by Prof. Miki Haseyama and Prof. Takahiro Ogawa. His research interests include Dataset Distillation, Self-Supervised Learning, Data-Centric AI, and Medical Image Analysis.

His research has been featured in renowned media, including Scientific American, Nikkei, NHK, Synced, AI Era, Deccan Herald, and Analytics India Magazine. He is the creator and maintainer of the Awesome Dataset Distillation project. He co-organized the 1st CVPR Workshop on Dataset Distillation and The First Dataset Distillation Challenge at ECCV. He has served as Area Chair for ACM MM and as a Program Committee Member for top-tier conferences such as NeurIPS, CVPR, ECCV, AAAI, and MICCAI. He also served as a Reviewer for prestigious journals such as TIP, TMI, MedIA, TNNLS, NN, TMM, and TCSVT. He is a member of IEEE.

I’m currently open to collaborating on dataset distillation and related topics! If you have any ideas, please feel free to drop me an email.

        

News

[2024/08] Call for Papers: Please check the NeurIPS Workshop on Dataset Distillation at NeurIPS 2024! I will serve as a Program Committee Member for this event! Thanks to Dr. George Cazenavette (MIT) for the invitation!

[2024/07] One paper was accepted to ACM MM 2024! Congrats to all collaborators!

[2024/06] One paper was early accepted to ICIP 2024! Congrats to Yaozong!

[2024/05] Call for Papers: Please check The First Dataset Distillation Challenge at ECCV 2024! I will serve as an Advising Committee Member for this event! Thanks to Prof. Yang You (NUS) for the invitation!

Biography

  • 2023/10 ~ Present Hokkaido University, Assistant Professor
  • 2022/04 ~ 2023/09 Hokkaido University, Ph.D. in Information Science
  • 2020/04 ~ 2022/03 Hokkaido University, M.S. in Information Science
  • 2015/09 ~ 2019/06 Dalian University of Technology, B.A. in Japanese
  • 2015/09 ~ 2019/06 Dalian University of Technology, B.S. in Software Engineering

Highlights

Awesome Dataset Distillation

NeurIPS Workshop on Dataset Distillation

The First Dataset Distillation Challenge

Publications

Journal

  • Susumu Horie, Shigeyuki Nakamae, Wataru Noguchi, Naoki Yamato, Guang Li, Hiroshi Tsutsui, Takeo Ohgane, “A study on trial of DX recurrent education program for working people in infrastructure field,” Journal of JSCE, vol. 80, no. 23, 2024. [Paper]
  • Guang Li, Ren Togo, Keisuke Maeda, Akinori Sako, Isao Yamauchi, Tetsuya Hayakawa, Shigeyuki Nakamae, Takahiro Ogawa, Miki Haseyama, “Automatic recognition of algal bed areas based on a large-scale semantic segmentation model for estimating CO2 absorption by blue carbon,” Journal of JSCE, vol. 80, no. 17, 2024. [Paper]
  • Guang Li, Ren Togo, Keisuke Maeda, Akinori Sako, Isao Yamauchi, Tetsuya Hayakawa, Shigeyuki Nakamae, Takahiro Ogawa, Miki Haseyama, “Algal bed region segmentation based on a ViT adapter using aerial images for estimating CO2 absorption capacity,” Remote Sensing, vol. 16, no. 10, 1742, 2024. [Paper] [Link]
  • Yuhu Feng, Jiahuan Zhang, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “A novel frame selection metric for video inpainting to enhance urban feature extraction,” Sensors, vol. 24, no. 10, 3035, 2024. [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Importance-aware adaptive dataset distillation,” Neural Networks, vol. 172, 106154, 2024. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Dataset distillation using parameter pruning,” IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E107-A, no. 6, pp. 936-940, 2024. [arXiv] [Paper]
  • Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Zero-shot traffic sign recognition based on midlevel feature matching,” Sensors, vol. 23, no. 23, 9607, 2023. [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Self-supervised learning for gastritis detection with gastric X-ray images,” International Journal of Computer Assisted Radiology and Surgery, vol. 18, no. 10, pp. 1841-1848, 2023. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Boosting automatic COVID-19 detection performance with self-supervised learning and batch knowledge ensembling,” Computers in Biology and Medicine, vol. 158, 106877, 2023. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “COVID-19 detection based on self-supervised transfer learning using chest X-ray images,” International Journal of Computer Assisted Radiology and Surgery, vol. 18, no. 4, pp. 715-722, 2023. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Compressed gastric image generation based on soft-label dataset distillation for medical data sharing,” Computer Methods and Programs in Biomedicine, vol. 227, 107189, 2022. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Dataset complexity assessment based on cumulative maximum scaled area under Laplacian spectrum,” Multimedia Tools and Applications, vol. 81, no. 22, pp. 32287-32303, 2022. [arXiv] [Paper]

International Conference

  • Ren Tasai, Guang Li, Ren Togo, Minghui Tang, Takaaki Yoshimura, Hiroyuki Sugimori, Kenji Hirata, Takahiro Ogawa, Kohsuke Kudo, Miki Haseyama, “Lung cancer classification using masked autoencoder pretrained on J-MID database,” IEEE Global Conference on Consumer Electronics (GCCE), Kokura, Japan, 2024. [Paper]
  • Ayaka Tsutsumi, Guang Li, Ren Togo, Takahiro Ogawa, Satoshi Kondo, Miki Haseyama, “Lung disease classification with limited training data based on weight selection technique,” IEEE Global Conference on Consumer Electronics (GCCE), Kokura, Japan, 2024. [Paper]
  • Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generative dataset distillation based on large model pool,” IEEE Global Conference on Consumer Electronics (GCCE), Kokura, Japan, 2024. [Paper]
  • Zhen Wang†, Dongyuan Li†, Guang Li, Ziqing Zhang, Renhe Jiang, “Multimodal low-light image enhancement with depth information,” ACM International Conference on Multimedia (ACM MM), Melbourne, Australia, 2024. [arXiv] [Paper]
  • Kai Wang, Ahmad Sajedi, …, Guang Li, …, Konstantinos N. Platanioits, Yang You, “Sometimes less is more: The first dataset distillation challenge,” European Conference on Computer Vision (ECCV) Workshops, Milano, Italy, 2024. [arXiv] [Paper] [Link]
  • Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Cross-domain few-shot in-context learning for enhancing traffic sign recognition,” IEEE International Conference on Image Processing (ICIP), Abu Dhabi, UAE, 2024. [arXiv] [Paper]
  • Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generative dataset distillation: balancing global structure and local details,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 7664-7671, Seattle, WA, USA, 2024. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Dataset distillation for medical dataset sharing,” AAAI Conference on Artificial Intelligence (AAAI) Workshops, pp. 1-6, Washington, DC, USA, 2023. [arXiv] [Link]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Self-knowledge distillation based self-supervised learning for COVID-19 detection from chest X-ray images,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1371-1375, Singapore, 2022. [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “TriBYOL: Triplet BYOL for self-supervised representation learning,” IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3458-3462, Singapore, 2022. (Top 10 self-supervised learning models in 2022) [arXiv] [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Self-supervised transfer learning for COVID-19 detection from chest X-ray images,” AAAI Conference on Artificial Intelligence (AAAI) Workshops, pp. 1-6, Vancouver, BC, Canada, 2022. [arXiv] [Link]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Triplet self-supervised learning for gastritis detection with scarce annotations,” IEEE Global Conference on Consumer Electronics (GCCE), pp. 787-788, Kyoto, Japan, 2021. [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Cross-view self-supervised learning via momentum statistics in batch normalization,” IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), pp. 1-2, Penghu, Taiwan, 2021. [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Complexity evaluation of medical image data for classification problem based on spectral clustering,” IEEE Global Conference on Consumer Electronics (GCCE), pp. 667-669, Kobe, Japan, 2020. (Best Student Paper Award) [Paper]
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Soft-label anonymous gastric X-ray image distillation,” IEEE International Conference on Image Processing (ICIP), pp. 305-309, Abu Dhabi, UAE, 2020. (The first paper to explore real-world dataset distillation) [arXiv] [Paper]

Domestic Conference

  • 堀江 進, 中前 茂之, 野口 渉, 大和 尚記, 李 広, 筒井 弘, 大鐘 武雄, “インフラ分野の社会人向けDXリカレント教育プログラムの試行に関する一考察,” 第42回建設マネジメント問題に関する研究発表・討論会, p. 1, 東京, 2024.
  • 李 広, 藤後 廉, 前田 圭介, 酒向 章哲, 山内 功, 早川 哲也, 中前 茂之, 小川 貴弘, 長谷山 美紀, “ブルーカーボンによるCO2吸収量推計へ向けた大規模セマンティックセグメンテーションモデルに基づく藻場領域の自動認識,” 第71回海岸工学講演会, p. 1, 秋田, 2024.
  • Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Fine-grained traffic sign recognition via cross-domain few-shot in-context learning,” Meeting on Image Recognition and Understanding (MIRU), pp. 1-5, Kumamoto, 2024.
  • Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generative dataset distillation considering global-local coherence,” Meeting on Image Recognition and Understanding (MIRU), pp. 1-5, Kumamoto, 2024.
  • 藤後 廉, 李 広, 小川 貴弘, 長谷山 美紀, “異分野連携によるデータ駆動型のAI研究に関する取組,” フォトエキサイトニクス研究拠点 第6回研究会, p. 1, 札幌, 2024.
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Dataset distillation via self-adaptive parameter matching,” Meeting on Image Recognition and Understanding (MIRU), pp. 1-5, Hamamatsu, 2023.
  • Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “A note on traffic sign recognition based on vision transformer adapter using visual feature matching,” ITE Technical Report, vol. 47, no. 6, pp. 208-211, Sapporo, 2023.
  • 李 広, 藤後 廉, 小川 貴弘, 長谷山 美紀, “医療データを対象としたデータセット蒸留に関する検討,” 第1回 北海道大学医療AIシンポジウム, p. 1, 札幌, 2022.
  • Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama, “COVID-19 detection based on masked image modeling using vision transformer,” Meeting on Image Recognition and Understanding (MIRU), pp. 1-4, Himeji, 2022.
  • Guang Li, Ren Togo, Katsuhiro Mabe, Shunpei Nishida, Yoshihiro Tomoda, Takahiro Ogawa, Miki Haseyama, “A note on automatic diagnosis of Helicobacter pylori infection based on self-supervised learning and self-knowledge distillation,” ITE Technical Report, vol. 46, no. 6, pp. 49-52, Sapporo, 2022.
  • Guang Li, Ren Togo, Katsuhiro Mabe, Shunpei Nishida, Yoshihiro Tomoda, Hikari Shimizu, Takahiro Ogawa, Miki Haseyama, “A note on automatic diagnosis of Helicobacter pylori infection based on EfficientNet with flooding loss,” ITE Technical Report, vol. 45, no. 4, pp. 23-26, Sapporo, 2021.
  • 李 広, 藤後 廉, 小川 貴弘, 長谷山 美紀, “nAULSに基づくデータセットの複雑性評価に関する検討,” 令和2年度 電気・情報関係学会北海道支部連合大会, pp. 98-99, 札幌, 2020.

Awards

  • The 2023 IEEE Sapporo Section Encouragement Award (2024/02)
  • The Dean’s Award (2023/09, Ph.D. Degree)
  • The First Hokkaido University Medical AI Symposium Outstanding Research Award (2022/11)
  • IEICE Hokkaido Section Student Encouragement Award (2022/03, M.S. Degree)
  • IEEE GCCE 2020 Best Student Paper Award (2020/10)
  • Outstanding Graduate of Dalian University of Technology (2019/06, B.S. and B.A. Degrees)

Funding

  • Hokkaido University-Hitachi Joint Cooperative Support Program for Education and Research (2022/04 ~ 2023/09) [Link]

Media Coverage

  • “CO2 60トン吸収認証 えりものブルーカーボン 雑海藻駆除しコンブ増,” 北海道新聞, 2024/01/10. [Link]
  • “北海道えりも町、ブルーカーボンでクレジット取得,” 日本経済新聞, 2024/01/05. [Link]
  • “CO2吸収量、森林の9倍 えりものコンブ 町の調査報告,” 北海道新聞, 2023/09/27. [Link]
  • “コンブで脱炭素推進 開発局がCO2吸収量初調査 漁業者の収入増も狙う,” 北海道新聞, 2023/07/01. [Link]
  • “えりも沿岸域でブルーカーボン 町などが検討会,” 北海道建設新聞, 2023/06/09. [Link]
  • “コンブのCO2吸収量、年内にも算出 えりも町など検討会発足,” 北海道新聞, 2023/06/07. [Link]
  • “えりも町 海中で二酸化炭素を吸収「ブルーカーボン」の検討会,” NHK NEWS WEB, 2023/06/07. [Link]
  • “北海道開発局、えりも町で「ブルーカーボン」調査,” 日本経済新聞, 2023/04/26. [Link]
  • “2022 Top10自监督学习模型发布! 美中两国8项成果霸榜,” 新智元, 2022/11/12. [Link]
  • “Top 10 Self-supervised Learning Models in 2022,” Analytics India Magazine, 2022/11/02. [Link]
  • “一个项目帮你了解数据集蒸馏Dataset Distillation,” 机器之心, 2022/10/09. [Link]
  • “Most Popular AI Research Aug 2022,” LibHunt, 2022/09/03. [Link]
  • “AIでインフラ点検 北海道大情報科学研究院,” 日本経済新聞, 2021/06/16. [Link]
  • “How to Make Artificial Intelligence More Democratic,” Scientific American, 2021/01/02. [Link]

Academic Service

Organizer

  • The First Dataset Distillation Challenge in conjunction with ECCV 2024
  • 1st CVPR Workshop on Dataset Distillation in conjunction with CVPR 2024

Area Chair

  • ACM International Conference on Multimedia (ACM MM) 2024

Program Committee Member

  • Conference on Neural Information Processing Systems (NeurIPS)
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • European Conference on Computer Vision (ECCV)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • British Machine Vision Conference (BMVC)
  • IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • IEEE International Conference on Visual Communications and Image Processing (VCIP)
  • IEEE Global Conference on Consumer Electronics (GCCE)
  • Meeting on Image Recognition and Understanding (MIRU)

Journal Reviewer

  • IEEE Transactions on Imaging Processing (TIP)
  • IEEE Transactions on Medical Imaging (TMI)
  • Medical Image Analysis (MedIA)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • Neural Networks (NN)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Transactions on Industrial Informatics (TII)
  • IEEE Transactions on Affective Computing (TAC)
  • IEEE Transactions on Artificial Intelligence (TAI)
  • + 15 Journals

Visitors

  unique visitors since 2022/02/13