数据稀缺下灾难性遗忘的最新进展：少样本类别增量学习的综合综述
Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
AI总结：
本文综述少样本类别增量学习（FSCIL）的最新进展，涵盖其目标、原型修正、预训练模型及语言引导新范式、性能分析与实际应用，提出挑战、解决方案与未来方向，助力应对数据稀缺下的持续学习问题。
摘要：
数据稀缺显著加剧了持续学习问题，即深度神经网络如何在仅有极少量样本的动态环境中学习。然而，少样本类别增量学习（FSCIL）方法及相关研究的最新进展，为解决该问题提供了富有洞察力的知识。本文对FSCIL进行了综合综述，重点关注几个重要方面：FSCIL方法全面且正式的目标、原型修正的重要性、基于预训练模型和语言引导机制的新学习范式、对FSCIL性能指标与评估的深入分析，以及FSCIL在各领域的实际应用场景。我们的广泛讨论还提出了FSCIL的开放挑战、潜在解决方案与未来方向。
英文摘要：
Data scarcity significantly complicates the continual learning problem, i.e., how a deep neural network learns in dynamic environments with very few samples. However, the latest progress of few-shot class incremental learning (FSCIL) methods and related studies show insightful knowledge on how to tackle the problem. This paper presents a comprehensive survey on FSCIL that highlights several important aspects i.e. comprehensive and formal objectives of FSCIL approaches, the importance of prototype rectifications, the new learning paradigms based on pre-trained model and language-guided mechanism, the deeper analysis of FSCIL performance metrics and evaluation, and the practical contexts of FSCIL in various areas. Our extensive discussion presents the open challenges, potential solutions, and future directions of FSCIL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
