NEWS お知らせ

2024年8月6日～9日に熊本で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MIRU2024にて，3件の口頭発表，11件のポスター発表を行いました！
また，様々な分野で活躍されている研究室OBとの交流会も行いました．

【口頭発表】

• He Zhu, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Reliable and Personalized Federated Learning with Prompt-based Method for Visual Question Answering in Medical Domain”
• Huaying Zhang, Rintaro Yanagi, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Integrating Query-target Relationship to Zero-shot Composed Image Retrieval from Masked Image-text Pairs”
• Taro Togo, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Refining Generative Class Incremental Learning Performance through Model Forgetting Strategies”

【ポスター発表】

• Longzhen Li, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Generative Dataset Distillation Considering Global-local Coherence”
• Masaki Kashiwagi, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Noisy Label Learning-based Self-consuming Iterative Re-training”
• Xiang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Strategic Classification Model Reinforcement: Introducing Language-guided Counterfactual Images to Identify and Address Classification Weaknesses”
• Ren Togo, Nao Nakagawa, Takahiro Ogawa, Miki Haseyama, “Exponential Dissimilarity-Dispersion Family for VAE-based Domain-Specific Representation Learning”
• Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Machine Unlearning Framework based on Aggregation of Gaussian Process-based Submodels”
• 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”
• Ziwen Lan, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Adversarial Attack Focused on Manipulating Semantic Information for Personalized Text-to-Image Diffusion Models”
• Yuki Era, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Metadata-independent Learning and Unified Dataset for Generalized Motion Generation Method”
• 岡村洋希, 前田圭介, 藤後廉, 小川貴弘, 長谷山美紀 (北大), “協調フィルタリングにおける潜在因子モデルの埋め込み表現のICAを用いた線形的構造の分析”
• 佐藤雅也, 前田圭介, 藤後廉, 小川貴弘, 長谷山美紀 (北大), “Identify-and-generate: VQAにおける大規模マルチモーダルモデルの獲得知識と視覚情報の統合強化”
• 七田亮, 藤後廉, 前田圭介, 小川貴弘, 長谷山美紀 (北大), “深層距離学習に基づく画像記憶性スコアの制御機構を導入したテキストからの画像生成に関する検討”