SEARCH
検索詳細李 広 (リ コウ)
| 数理・データサイエンス教育研究センター 産学官・地域連携部門 | 助教 |
Guang Li is an Assistant Professor at the Education and Research Center for Mathematical and Data Science, Hokkaido University, and a member of the Laboratory of Media Dynamics. He received dual bachelor’s degrees in Software Engineering and 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, respectively, under the supervision of Prof. Miki Haseyama and Prof. Takahiro Ogawa. He also collaborates closely with Prof. Konstantinos N. Plataniotis at the University of Toronto. His research interests include dataset distillation, data-efficient learning, representation learning, and generative modeling, with applications to real-world problems such as medical imaging.
He authored one of the earliest works on dataset distillation and has been contributing to the field since, maintaining Awesome-Dataset-Distillation and co-organizing the first CVPR Workshop on Dataset Distillation and the first Dataset Distillation Challenge at ECCV. He received the 2024 IEEE Sapporo Young Professionals Best Researcher Award for contributions to dataset distillation. He has served as an Area Chair for ACM MM, MICCAI, and ICASSP, as a program committee member for NeurIPS, ICLR, ICML, CVPR, ICCV, and ECCV, and as a reviewer for leading journals including TPAMI, IJCV, TIP, and TMI, for which he was recognized with the ICML 2026 Gold Reviewer Award and named an Outstanding Reviewer for ECCV 2026. His research has received international media coverage from outlets including Scientific American, Nikkei, and NHK.
E-mail: guang@lmd.ist.hokudai.ac.jp
研究者基本情報
■ 学位■ URL
researchmap URL■ ID 各種
研究者番号
- 20994510
研究キーワード研究分野
経歴
■ 経歴学歴
- 2022年04月 - 2023年09月, 北海道大学, 大学院情報科学院, 博士後期課程, 日本国
- 2020年04月 - 2022年03月, 北海道大学, 大学院情報科学院, 修士課程, 日本国
- 2015年09月 - 2019年06月, 大連理工大学, ソフトウェア工学部, 中華人民共和国
- 2026年07月 - 現在
MIRAI Driving: Multimodal Intelligence and Reasoning for Autonomous and Intelligent Driving in conjunction with ACCV 2026, Orginizer - 2026年06月 - 現在
International Joint Conference on Neural Networks (IJCNN) 2027, Area Chair - 2025年11月 - 現在
International Journal of Computer Vision (IJCV), Reviewer - 2025年08月 - 現在
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Reviewer - 2024年06月 - 現在
IEEE Transactions on Image Processing (TIP), Reviewer - 2024年02月 - 現在
IEEE Transactions on Multimedia (TMM), Reviewer - 2024年02月 - 現在
IEEE Transactions on Medical Imaging (TMI), Reviewer - 2026年02月 - 2026年07月
ACM International Conference on Multimedia (ACM MM) 2026, Area Chair - 2026年02月 - 2026年04月
第29回 画像の認識・理解シンポジウム, シニア評価委員 - 2026年01月 - 2026年03月
International Joint Conference on Neural Networks (IJCNN) 2026, Area Chair - 2025年09月 - 2026年02月
International Conference on Medical Imaging with Deep Learning (MIDL) 2026, Area Chair - 2025年09月 - 2026年01月
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2026, Area Chair - 2025年02月 - 2025年06月
ACM International Conference on Multimedia (ACM MM) 2025, Area Chair - 2025年01月 - 2025年06月
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2025, Area Chair - 2025年02月 - 2025年05月
第28回 画像の認識・理解シンポジウム, シニア評価委員 - 2024年12月 - 2025年03月
International Joint Conference on Neural Networks (IJCNN) 2025, Area Chair - 2024年11月 - 2025年03月
International Conference on Medical Imaging with Deep Learning (MIDL) 2025, Area Chair - 2024年10月 - 2024年12月
IEEE International Symposium on Biomedical Imaging (ISBI) 2025, Area Chair - 2024年04月 - 2024年09月
The First Dataset Distillation Challenge in conjunction with ECCV 2024, Organizer - 2024年01月 - 2024年07月
ACM International Conference on Multimedia (ACM MM) 2024, Area Chair - 2024年02月 - 2024年06月
The First CVPR Workshop on Dataset Distillation in conjunction with CVPR 2024, Organizer - 2024年02月 - 2024年05月
第27回 画像の認識・理解シンポジウム, シニア評価委員, 学協会 - 2023年02月 - 2023年04月
第26回 画像の認識・理解シンポジウム, ジュニア評価委員, 学協会 - 2022年03月 - 2022年05月
第25回 画像の認識・理解シンポジウム, ジュニア評価委員, 学協会
研究活動情報
■ 受賞- 2026年08月, MIRU 2026 Best Reviewer Award
- 2026年07月, ECCV 2026 Outstanding Reviewer
- 2026年05月, ICML 2026 Gold Reviewer Award
- 2025年09月, IEEE GCCE 2025 Excellent Student Poster Award Outstanding Prize
- 2025年05月, The Ports and Harbours Association of Japan Best Paper Award
- 2024年11月, 令和6年度電気・情報関係学会北海道支部連合大会 若手優秀論文発表賞
- 2024年11月, IEEE GCCE 2024 Presentation Award
- 2024年09月, ECCV 2024 The First Dataset Distillation Challenge Track 2 Third Place
- 2024年07月, The 2024 IEEE Sapporo YP Best Researcher Award
- 2024年02月, The 2023 IEEE Sapporo Section Encouragement Award
- 2023年09月, The Dean’s Award
- 2022年11月, The First Hokkaido University Medical AI Symposium Outstanding Research Award
- 2022年03月, IEICE Hokkaido Section Student Encouragement Award
- 2020年10月, IEEE GCCE 2020 Excellent Student Paper Award Gold Prize
- 2019年06月, Outstanding Graduate of Dalian University of Technology
- Classifier-Derived Guidance for Diffusion-Based Medical Dataset Distillation
Shuailin Du; Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
Bioengineering, 2026年09月23日
研究論文(学術雑誌) - EVLF: Early Vision-Language Fusion for Generative Dataset Distillation
Wenqi Cai; Yawen Zou; Guang Li; Chunzhi Gu; Chao Zhang
CVPR 2026, 33953, 33962, 2026年06月, [査読有り] - SAS: Semantic-Aware Sampling for Generative Dataset Distillation
Mingzhuo Li; Guang Li; Linfeng Ye; Jiafeng Mao; Takahiro Ogawa; Konstantinos N. Plataniotis; Miki Haseyama
IEEE Open Journal of Signal Processing, 7, 668, 677, Institute of Electrical and Electronics Engineers (IEEE), 2026年06月, [査読有り]
研究論文(学術雑誌) - Adaptive Shared Experts with Lora-Based Mixture of Experts for Multi-Task Learning
Minghao Yang; Ren Togo; Guang Li; Takahiro Ogawa; Miki Haseyama
ICASSP 2026, 1096, 1100, IEEE, 2026年05月, [査読有り]
研究論文(国際会議プロシーディングス) - ASMIL: Attention-Stabilized Multiple Instance Learning for Whole-Slide Imaging
Linfeng Ye; Shayan Mohajer Hamidi; Zhixiang Chi; Guang Li; Mert Pilanci; Takahiro Ogawa; Miki Haseyama; Konstantinos N. Plataniotis
ICLR 2026, 1, 39, 2026年04月, [査読有り] - Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV
Wenbo Huang; Jinghui Zhang; Zhenghao Chen; Guang Li; Lei Zhang; Yang Cao; Fang Dong; Takahiro Ogawa; Miki Haseyama
AAAI 2026, 40, 7, 5140, 5148, Association for the Advancement of Artificial Intelligence (AAAI), 2026年03月, [査読有り]
研究論文(学術雑誌), Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging because of the background distractions. Receptance Weighted Key Value (RWKV), which learns interaction between various dimensions, shows promise for global modeling. While directly applying RWKV to wide-angle FSAR may fail to highlight subjects due to excessive background information. Additionally, temporal relation degraded by frames with similar backgrounds is difficult to reconstruct, further impacting performance. Therefore, we design the CompOund SegmenTation and Temporal REconstructing RWKV (Otter). Specifically, the Compound Segmentation Module (CSM) is devised to segment and emphasize key patches in each frame, effectively highlighting subjects against background information. The Temporal Reconstruction Module (TRM) is incorporated into the temporal-enhanced prototype construction to enable bidirectional scanning, allowing better reconstruct temporal relation. Furthermore, a regular prototype is combined with the temporal-enhanced prototype to simultaneously enhance subject emphasis and temporal modeling, improving wide-angle FSAR performance. Extensive experiments on benchmarks such as SSv2, Kinetics, UCF101, and HMDB51 demonstrate that Otter achieves state-of-the-art performance. Extra evaluation on the VideoBadminton dataset further validates the superiority of Otter in wide-angle FSAR. - Dual-model weight selection and self-knowledge distillation for medical image classification
Ayaka Tsutsumi; Guang Li; Ren Togo; Takahiro Ogawa; Satoshi Kondo; Miki Haseyama
Computers in Biology and Medicine, 204, 111510, 111510, Elsevier BV, 2026年03月, [査読有り]
研究論文(学術雑誌) - Reimagining tourism pedestrian street aesthetics through machine learning: Understanding the role of spatial form based on a case study in Luoyang, China
Xin Gao; Hirofumi Ueda; Meng Qu; Guang Li; Xiaojin Li; Menglin Xu
Frontiers of Architectural Research, 15, 1, 238, 258, Elsevier BV, 2026年02月, [査読有り]
研究論文(学術雑誌) - Hyperbolic Dataset Distillation
Wenyuan Li; Guang Li; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
NeurIPS 2025, 75120, 75151, Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2025年12月, [査読有り], [責任著者]
研究論文(国際会議プロシーディングス) - Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness
Ren Tasai; Guang Li; Ren Togo; Takahiro Ogawa; Kenji Hirata; Minghui Tang; Takaaki Yoshimura; Hiroyuki Sugimori; Noriko Nishioka; Yukie Shimizu; Kohsuke Kudo; Miki Haseyama
Bioengineering, 13, 1, 32, 32, MDPI AG, 2025年12月, [査読有り], [招待有り]
研究論文(学術雑誌), We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly generalizable model in medical image diagnosis is challenging, mainly because of issues, such as the scarcity of large-scale, accurately annotated datasets and domain shifts inherent to dynamic healthcare environments. Specifically, in chest CT, these domain shifts often arise from differences in window settings, which are optimized for distinct clinical purposes. Previous CSSL frameworks often mitigated domain shift by reusing past data, a typically impractical approach owing to privacy constraints. Our approach addresses these challenges by effectively capturing the relationship between previously learned knowledge and new information across different training stages through continual pretraining on unlabeled images. Specifically, by incorporating a latent replay-based mechanism into CSSL, our method mitigates catastrophic forgetting due to domain shifts during continual pretraining while ensuring data privacy. Additionally, we introduce a feature distillation technique that integrates Wasserstein distance-based knowledge distillation and batch-knowledge ensemble, enhancing the ability of the model to learn meaningful, domain-shift-robust representations. Finally, we validate our approach using chest CT images obtained across two different window settings, demonstrating superior performance compared with other approaches. - Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
Mingzhuo Li; Guang Li; Jiafeng Mao; Linfeng Ye; Takahiro Ogawa; Miki Haseyama
ICCV 2025 Workshop, 6853, 6860, IEEE, 2025年10月, [査読有り]
研究論文(国際会議プロシーディングス) - Dataset Distillation Via Vision-Language Category Prototype
Yawen Zou; Guang Li; Duo Su; Zi Wang; Jun Yu; Chao Zhang
ICCV 2025, 2941, 2950, IEEE, 2025年10月, [査読有り]
研究論文(国際会議プロシーディングス) - Cross-domain multi-step thinking: Zero-shot fine-grained traffic sign recognition in the wild
Yaozong Gan; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
Knowledge-Based Systems, 327, 114172, 114172, 2025年10月, [査読有り], [国際誌]
研究論文(学術雑誌) - Enhancing Medical Dataset Distillation Based on Classifier-Guided Diffusion Model
Shuailin Du; Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
GCCE 2025, 248, 249, IEEE, 2025年09月, [査読有り]
研究論文(国際会議プロシーディングス) - GeoJapan Fusion Framework: A Large Multimodal Model for Regional Remote Sensing Recognition
Yaozong Gan; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
Remote Sensing, 17, 17, 3044, 3044, MDPI, 2025年09月, [査読有り], [招待有り], [国際誌]
研究論文(学術雑誌) - Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory
Mingzhuo Li; Guang Li; Jiafeng Mao; Takahiro Ogawa; Miki Haseyama
ICIP 2025, 415, 420, IEEE, 2025年09月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Clarifying diagnostic scope and future perspectives in AI-assisted diagnosis of Helicobacter pylori infection
Guang Li; Katsuhiro Mabe; Miki Haseyama
Journal of Gastroenterology, Springer Science and Business Media LLC, 2025年06月, [査読有り], [招待有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - LiDAR-assisted image restoration for extreme low-light conditions
Zhen Wang; Yaozu Wu; Dongyuan Li; Guang Li; Peide Zhu; Ziqing Zhang; Renhe Jiang
Knowledge-Based Systems, 316, 113382, 113382, Elsevier BV, 2025年05月, [査読有り], [国際共著], [国際誌]
研究論文(学術雑誌) - Generative Dataset Distillation Based on Self-knowledge Distillation
Longzhen Li; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
ICASSP 2025, 1, 5, IEEE, 2025年04月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images
Ren Tasai; Guang Li; Ren Togo; Minghui Tang; Takaaki Yoshimura; Hiroyuki Sugimori; Kenji Hirata; Takahiro Ogawa; Kohsuke Kudo; Miki Haseyama
ICASSP 2025, 1, 5, IEEE, 2025年04月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
Wenbo Huang; Jinghui Zhang; Guang Li; Lei Zhang; Shuoyuan Wang; Fang Dong; Jiahui Jin; Takahiro Ogawa; Miki Haseyama
AAAI 2025, 3751, 3759, Association for the Advancement of Artificial Intelligence (AAAI), 2025年03月, [査読有り], [国際共著], [国際誌]
研究論文(学術雑誌) - A STUDY ON THE PRACTICE OF DX RECURRENT EDUCATION PROGRAM FOR WORKING PEOPLE IN INFRASTRUCTURE FIELD
Susumu HORIE; Shigeyuki NAKAMAE; Wataru NOGUCHI; Naoki YAMATO; Guang LI; Hiroshi TSUTSUI; Takeo OHGANE
Journal of JSCE, 80, 23, Japan Society of Civil Engineers, 2025年02月, [査読有り], [国内誌]
研究論文(学術雑誌) - Multistage deep learning for classification of Helicobacter pylori infection status using endoscopic images
Guang Li; Ren Togo; Katsuhiro Mabe; Shunpei Nishida; Yoshihiro Tomoda; Fumiyuki Shiratani; Masashi Hirota; Takahiro Ogawa; Miki Haseyama
Journal of Gastroenterology, 60, 4, 408, 415, Springer Science and Business Media LLC, 2025年01月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - Handling Class Imbalance in Black-Box Unsupervised Domain Adaptation with Synthetic Minority Over-Sampling
Yawen Zou; Chunzhi Gu; Zi Wang; Guang Li; Jun Yu; Chao Zhang
VCIP 2024, 1, 5, IEEE, 2024年12月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - AUTOMATIC RECOGNITION OF ALGAL BED AREAS BASED ON A LARGE-SCALE SEMANTIC SEGMENTATION MODEL FOR ESTIMATING CO<sub>2</sub> ABSORPTION BY BLUE CARBON
Guang LI; Ren TOGO; Keisuke MAEDA; Akinori SAKO; Isao YAMAUCHI; Tetsuya HAYAKAWA; Shigeyuki NAKAMAE; Takahiro OGAWA; Miki HASEYAMA
Journal of JSCE, 80, 17, Japan Society of Civil Engineers, 2024年11月, [査読有り], [筆頭著者], [国内誌]
研究論文(学術雑誌) - Lung Disease Classification with Limited Training Data Based on Weight Selection Technique
Ayaka Tsutsumi; Guang Li; Ren Togo; Takahiro Ogawa; Satoshi Kondo; Miki Haseyama
GCCE 2024, 460, 461, IEEE, 2024年10月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Generative Dataset Distillation Based on Large Model Pool
Longzhen Li; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
GCCE 2024, 458, 459, IEEE, 2024年10月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Lung Cancer Classification Using Masked Autoencoder Pretrained on J-MID Database
Ren Tasai; Guang Li; Ren Togo; Minghui Tang; Takaaki Yoshimura; Hiroyuki Sugimori; Kenji Hirata; Takahiro Ogawa; Kohsuke Kudo; Miki Haseyama
GCCE 2024, 456, 457, IEEE, 2024年10月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Multimodal Low-light Image Enhancement with Depth Information
Zhen Wang; Dongyuan Li; Guang Li; Ziqing Zhang; Renhe Jiang
ACM MM 2024, 4976, 4985, ACM, 2024年10月, [査読有り], [国際共著], [国際誌]
研究論文(国際会議プロシーディングス) - Cross-Domain Few-Shot In-Context Learning For Enhancing Traffic Sign Recognition
Yaozong Gan; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
ICIP 2024, 2564, 2570, IEEE, 2024年10月, [査読有り], [国際誌]
研究論文(国際会議プロシーディングス) - Generative Dataset Distillation Based on Diffusion Model
Duo Su; Junjie Hou; Guang Li; Ren Togo; Rui Song; Takahiro Ogawa; Miki Haseyama
ECCV 2024 Workshop, 83, 94, Springer Nature Switzerland, 2024年09月, [査読有り], [責任著者], [国際共著], [国際誌]
論文集(書籍)内論文 - RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
ECCV 2024 Workshop, 148, 157, Springer Nature Switzerland, 2024年09月, [査読有り], [筆頭著者, 責任著者], [国際誌]
論文集(書籍)内論文 - Generative Dataset Distillation: Balancing Global Structure and Local Details
Longzhen Li; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
CVPR 2024 Workshop, 7664, 7671, 2024年06月, [査読有り], [国際誌]
研究論文(学術雑誌) - Algal Bed Region Segmentation Based on a ViT Adapter Using Aerial Images for Estimating CO2 Absorption Capacity
Guang Li; Ren Togo; Keisuke Maeda; Akinori Sako; Isao Yamauchi; Tetsuya Hayakawa; Shigeyuki Nakamae; Takahiro Ogawa; Miki Haseyama
Remote Sensing, 16, 10, 1742, 1742, MDPI, 2024年05月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - A Novel Frame-Selection Metric for Video Inpainting to Enhance Urban Feature Extraction
Yuhu Feng; Jiahuan Zhang; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
Sensors, 24, 10, 3035, 3035, MDPI, 2024年05月, [査読有り], [国際誌]
研究論文(学術雑誌) - Importance-aware adaptive dataset distillation
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
Neural Networks, 172, 106154, 106154, 2024年04月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - Dataset Distillation Using Parameter Pruning
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 107, 6, 936, 940, 2024年, [査読有り], [筆頭著者], [国内誌]
研究論文(学術雑誌) - Zero-Shot Traffic Sign Recognition Based on Midlevel Feature Matching
Yaozong Gan; Guang Li; Ren Togo; Keisuke Maeda; Takahiro Ogawa; Miki Haseyama
Sensors, 23, 23, 9607, 9607, MDPI, 2023年12月, [査読有り], [国際誌]
研究論文(学術雑誌) - Self-supervised learning for gastritis detection with gastric X-ray images
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
International Journal of Computer Assisted Radiology and Surgery, 18, 10, 1841, 1848, 2023年10月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - Boosting automatic COVID-19 detection performance with self-supervised learning and batch knowledge ensembling
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
Computers in Biology and Medicine, 158, 106877, 106877, 2023年05月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - COVID-19 detection based on self-supervised transfer learning using chest X-ray images
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
International Journal of Computer Assisted Radiology and Surgery, 18, 4, 715, 722, 2023年04月, [査読有り], [筆頭著者], [国際誌]
研究論文(学術雑誌) - Dataset distillation for medical dataset sharing
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
AAAI 2023 Workshop, 1, 6, 2023年02月, [査読有り], [筆頭著者, 責任著者], [国際誌] - Compressed gastric image generation based on soft-label dataset distillation for medical data sharing
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
Computer Methods and Programs in Biomedicine, 227, 107189, 107189, Elsevier BV, 2022年12月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(学術雑誌) - TriBYOL: Triplet BYOL for Self-Supervised Representation Learning
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
ICASSP 2022, 3458, 3462, IEEE, 2022年05月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス) - Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
ICASSP 2022, 1371, 1375, IEEE, 2022年05月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス) - Dataset complexity assessment based on cumulative maximum scaled area under Laplacian spectrum
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
Multimedia Tools and Applications, 81, 22, 32287, 32303, Springer Science and Business Media LLC, 2022年04月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(学術雑誌) - Self-supervised transfer learning for COVID-19 detection from chest X-ray images
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
AAAI 2022 Workshop, 1, 6, 2022年03月, [査読有り], [筆頭著者, 責任著者], [国際誌] - Triplet Self-Supervised Learning for Gastritis Detection with Scarce Annotations
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
GCCE 2021, 787, 788, IEEE, 2021年10月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス) - Cross-view Self-supervised Learning via Momentum Statistics in Batch Normalization
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
ICCE-TW 2021, 1, 2, IEEE, 2021年09月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス) - Soft-Label Anonymous Gastric X-Ray Image Distillation
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
ICIP 2020, 305, 309, IEEE, 2020年10月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス) - Complexity Evaluation of Medical Image Data for Classification Problem Based on Spectral Clustering
Guang Li; Ren Togo; Takahiro Ogawa; Miki Haseyama
GCCE 2020, 667, 669, IEEE, 2020年10月, [査読有り], [筆頭著者, 責任著者], [国際誌]
研究論文(国際会議プロシーディングス)
■ 共同研究・競争的資金等の研究課題
- 拡散モデルに基づく生成型データセット蒸留技術の構築
科学研究費助成事業
2024年07月31日 - 2026年03月31日
李 広
本研究では,ラベルなしデータを活用した自己教師あり表現学習を拡散モデルに基づいて実現することで,学習プロセスの効率化とデータプライバシーの確保を両立する新しいデータセット蒸留技術の構築を目的としている.フェーズ1では,拡散モデルを用いた表現学習技術を構築し,フェーズ2では,プライバシー保護を考慮した生成型データセット蒸留技術の実装を目指している.本研究の着想は,近年急速に注目される大規模拡散モデルと,AIの民主化を志向するデータ軽量化技術の統合にあり,医療・インフラなど高い匿名性と汎用性が求められる分野において重要な役割を果たすことが期待される.
本年度は,拡散モデルを用いたデータセット蒸留手法を新たに提案し,その有効性を国際的に示した.本成果は,中国・香港・ドイツとの国際連携研究として実施され,コンピュータビジョン分野のトップ会議ECCV 2024にて開催された「第1回データセット蒸留チャレンジ」において第3位を受賞した.さらに,本技術の拡張版は,ICIP 2025およびICCV 2025に投稿中である.また,申請者はCVPR 2024およびECCV 2024のワークショップ委員として分野形成に貢献し,2024 IEEE Sapporo Young Professionals Best Researcher Awardの受賞および招待講演(The 4th Hokkaido YP Workshop)を行うなど,対外的な研究発信も積極的に展開した.
日本学術振興会, 研究活動スタート支援, 北海道大学, 24K23849
