過去のお知らせ
米国アラスカ・アンカレッジ（9/14-18）で開催された世界最大規模の画像処理系国際会議IEEE ICIP 2025にて当研究室から3件の発表を行いました！
①Mingzhuo Li, Guang Li, Jiafeng Mao, Takahiro Ogawa, Miki Haseyama, “DIVERSITY-DRIVEN GENERATIVE DATASET DISTILLATION BASED ON DIFFUSION MODEL WITH SELF-ADAPTIVE MEMORY”
②Koshiro Toishi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “ENHANCING ADVERSARIAL ROBUSTNESS OF FOUNDATION MODELS WITHOUT DATA CENTRALIZATION”
③Kaede Hayakawa, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “OUT-OF-DISTRIBUTION SAMPLE SELECTION GENERATED BY DIFFUSION MODEL TOWARD MODEL GENERALIZATION”
