Practical Continual Forgetting for Pre-trained Vision Models
实用的预训练视觉模型持续遗忘
机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所,中国科学院) ; University of Chinese Academy of Sciences(中国科学院大学) ; Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(人工智能与机器人中心,香港科学创新研究院,中国科学院) ; SenseTime Research(商汤科技研究院)
AI总结 该研究提出GS-LoRA方法,通过组稀疏正则化和原型信息监督,实现预训练视觉模型的持续遗忘,有效删除特定类别信息同时最小化对其他类别的影响。
Comments Accepted by TPAMI. arXiv admin note: substantial text overlap with arXiv:2403.11530