解决数据稀缺下持续学习的遗忘问题，系统梳理少样本增量学习前沿进展。
Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
- 提出原型修正机制，缓解新类学习中的模型遗忘。
- 基于预训练模型与语言引导，提升小样本下的泛化能力。
- 适合关注持续学习、小样本场景的科研与工程人员。
数据稀缺极大增加了持续学习的难度，即如何在动态环境中用极少样本训练深度神经网络。然而，近期少样本类增量学习（FSCIL）方法及相关研究揭示了应对该问题的重要洞见。本文对FSCIL进行了全面综述，重点涵盖：FSCIL方法的系统性目标定义、原型修正的重要性、基于预训练模型与语言引导的新学习范式、对性能评估指标与实验设置的深入分析，以及在多个实际场景中的应用。本文还探讨了当前开放挑战、潜在解决方案与未来研究方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。