面向少样本类增量学习的演进式字典表示（英文版）

英文标题：Evolving Dictionary Representation for Few-shot Class-incremental Learning中文摘要：本文提出了一种解决 few-shot class-incremental learning 问题的方法，使用深度字典学习和视觉表示学习相结合的混合学习架构，同时在基础阶段优化字典和特征提取，而只在增量阶段对字典进行优化以适应新的类别，同时在基础训练中加入多个伪类以便未来新概念的适应。经过实验验证，该方法有效性得到了证实。英文摘要：New objects are continuously emerging in the dynamically changing world and areal-world artificial intelligence system should be capable of continual andeffectual adaptation to new emerging classes without forgetting old ones. Inview of this, in thi