過去のお知らせ
2025年7月29日～8月1日に京都にて開催された国内最大規模の画像の認識・理解シンポジウムMIRU2025にて4件の口頭発表、9件のポスターを発表しました!
2025年7月29日～8月1日に京都にて開催された国内最大規模の画像の認識・理解シンポジウムMIRU2025にて4件の口頭発表、9件のポスターを発表しました!
【口頭発表】
- 渡部航史, 前田圭介, 小川貴弘, 長谷山美紀 (北大), “データの大域構造を考慮した近傍埋め込み手法に基づく深層表現の可視化”
- Kenta Uesugi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Leveraging Counterfactuals for Automatic Composed Image Retrieval Dataset Generation with In-context Learning”
- Ren Togo, Ryo Shichida, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Efficient Fine-Tuning and Uncertainty-Aware Personalized Federated Learning for Medical Vision-Language Models”
- He Zhu, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Efficient Fine-Tuning and Uncertainty-Aware Personalized Federated Learning for Medical Vision-Language Models”
【ポスター発表】
- Yuiko Uchida, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “An Object-Focused Metric for 3D Scene Evaluation Based on Features of an Object Detection Model”
- Kaede Hayakawa, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “OOD Reduction of Generated Image by Diffusion Model toward Data Augmentation”
- Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Adversarial Perturbation to Prevent Concept Bleed-through in Continual Learning of Personalized Generative Models”
- Koshiro Toishi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Robust Adversarial Defense Against Multiple Attacks Without Data Centralization”
- Ryota Goka, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Near-miss accident anticipation using video images on construction machinery”
- Masaki Yoshida, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Novel-view Acoustic Synthesis Based on Audio Point Cloud Optimization”
- Mingzhuo Li, Guang Li (Hokkaido Univ.), Jiafeng Mao (UTokyo), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.), “Self-Adaptive Memory for Diversity-Driven Dataset Distillation Using Diffusion Model”
- Ayaka Tsutsumi, Guang Li, Ren Togo, Takahiro Ogawa (Hokkaido Univ.), Satoshi Kondo (Muroran Institute of Technology), Miki Haseyama (Hokkaido Univ.), “Medical Image Classification Based on Dual Model Weight Selection and Self-Knowledge Distillation”
- Ren Tasai, Guang Li, Ren Togo, Minghui Tang, Takaaki Yoshimura, Hiroyuki Sugimori, Kenji Hirata, Takahiro Ogawa, Kohsuke Kudo, Miki Haseyama (Hokkaido Univ.), “Privacy-aware Domain-Incremental Continual Self-Supervised Learning for Chest CT Images”
また、以下の賞を受賞しました！
【MIRUオーディエンス賞】
- 渡部航史
【MIRU学生奨励賞】
- 渡部航史、朱赫、上杉健大
【評価貢献賞】
- 前田圭介先生
