Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
This survey addresses the problem of continual learning under data scarcity for researchers and practitioners in the field of deep learning.
This survey tackles the problem of catastrophic forgetting in deep neural networks under data scarcity, presenting the latest advancements in few-shot class incremental learning. The result is a comprehensive overview of the field, highlighting key aspects and open challenges.
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.