Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta-learning based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective.

翻译：大型深度学习模型令人印象深刻，但在实时数据不可用时则表现不佳。小样本类增量学习（FSCIL）对深度神经网络提出了重大挑战，要求其仅从少量带标签样本中学习新任务，同时不遗忘先前学到的知识。这种设置极易引发灾难性遗忘和过拟合问题，严重影响模型性能。研究FSCIL有助于克服深度学习模型在数据量和获取时间上的局限性，同时提升机器学习模型的实用性和适应性。本文对FSCIL进行了全面综述。与以往综述不同，我们旨在综合小样本学习和增量学习，从两个角度重点介绍FSCIL，同时回顾了30余项理论研究和20余项应用研究。从理论角度，我们提出了一种新颖的分类方法，将该领域分为五个子类别，包括传统机器学习方法、基于元学习的方法、基于特征与特征空间的方法、基于回放的方法以及基于动态网络结构的方法。我们还评估了近期理论研究在FSCIL基准数据集上的性能。从应用角度，FSCIL在图像分类、目标检测和图像分割等计算机视觉领域，以及自然语言处理和图中均取得了令人瞩目的成果。我们总结了这些重要应用。最后，我们指出了潜在的未来研究方向，包括应用、问题设置和理论发展。总体而言，本文从方法、性能和应用角度全面分析了FSCIL的最新进展。