محفوظ في:
التفاصيل البيبلوغرافية
المؤلفون الرئيسيون: Xing, Mingyu, Cheng, Lechao, Tang, Shengeng, Wang, Yaxiong, Zhong, Zhun, Wang, Meng
التنسيق: Preprint
منشور في: 2025
الموضوعات:
الوصول للمادة أونلاين:https://arxiv.org/abs/2502.08075
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
جدول المحتويات:
  • We introduce \textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\-specified information, retaining essential knowledge, and acquiring new knowledge simultaneously. By delving into the analysis of knock-on feature hierarchy, we find that incremental learning typically progresses from low\-level representations to higher\-level semantics, whereas forgetting tends to occur in the opposite direction\-starting from high-level semantics and moving down to low-level features. Building upon this, we propose to benchmark the knowledge swapping task with the strategy of \textit{Learning Before Forgetting}. Comprehensive experiments on various tasks like image classification, object detection, and semantic segmentation validate the effectiveness of the proposed strategy. The source code is available at \href{https://github.com/xingmingyu123456/KnowledgeSwapping}{https://github.com/xingmingyu123456/KnowledgeSwapping}.