TaskVAE：用于人类活动识别持续学习中样本生成的任务特定变分自编码器
TaskVAE: Task-Specific Variational Autoencoders for Exemplar Generation in Continual Learning for Human Activity Recognition
AI总结：
本文提出TaskVAE框架，通过任务特定变分自编码器为类别增量持续学习生成合成回放样本，在仅需极低内存的情况下解决了人类活动识别中的灾难性遗忘问题，并在多个数据集上验证了其优越性。
摘要：
随着基于机器学习的系统日益融入日常生活，它们带来了新的机遇，但也面临适应动态数据环境的挑战。各种形式的数据偏移——渐进的、突发的或周期性的——威胁着模型精度，使得持续适应变得至关重要。持续学习（CL）使模型能够从不断演变的数据流中学习，同时尽量减少对先前知识的遗忘。在CL策略中，基于回放的方法已被证明是有效的，但其成功依赖于在内存约束与在学习新类别的同时保持旧类别精度之间取得平衡。本文提出了TaskVAE，一个用于类别增量场景下基于回放的持续学习框架。TaskVAE采用任务特定的变分自编码器（VAE）从先前任务中生成合成样本，然后将这些样本与新任务数据一起用于训练分类器。与需要预先知道总类别数或依赖单一VAE处理所有任务的传统方法不同，TaskVAE能够灵活适应不断增加的任务，而无需此类约束。我们专注于使用配备IMU传感器设备的人类活动识别（HAR）。与以往将所有用户数据合并的HAR研究不同，我们的方法聚焦于单个用户的数据，更好地反映了个人逐步学习新活动的真实场景。在5个不同的HAR数据集上的大量实验表明，TaskVAE优于经验回放方法，尤其是在数据有限的情况下，并且随着数据集规模的增大表现出稳健的性能。此外，TaskVAE的内存占用极小，仅相当于每个任务60个样本，同时仍能生成无限数量的合成样本。其贡献在于平衡内存约束、任务特定生成和长期稳定性，使其成为HAR等领域实际应用的可靠解决方案。
英文摘要：
As machine learning based systems become more integrated into daily life, they unlock new opportunities but face the challenge of adapting to dynamic data environments. Various forms of data shift-gradual, abrupt, or cyclic-threaten model accuracy, making continual adaptation essential. Continual Learning (CL) enables models to learn from evolving data streams while minimizing forgetting of prior knowledge. Among CL strategies, replay-based methods have proven effective, but their success relies on balancing memory constraints and retaining old class accuracy while learning new classes. This paper presents TaskVAE, a framework for replay-based CL in class-incremental settings. TaskVAE employs task-specific Variational Autoencoders (VAEs) to generate synthetic exemplars from previous tasks, which are then used to train the classifier alongside new task data. In contrast to traditional methods that require prior knowledge of the total class count or rely on a single VAE for all tasks, TaskVAE adapts flexibly to increasing tasks without such constraints. We focus on Human Activity Recognition (HAR) using IMU sensor-equipped devices. Unlike previous HAR studies that combine data across all users, our approach focuses on individual user data, better reflecting real-world scenarios where a person progressively learns new activities. Extensive experiments on 5 different HAR datasets show that TaskVAE outperforms experience replay methods, particularly with limited data, and exhibits robust performance as dataset size increases. Additionally, memory footprint of TaskVAE is minimal, being equivalent to only 60 samples per task, while still being able to generate an unlimited number of synthetic samples. The contributions lie in balancing memory constraints, task-specific generation, and long-term stability, making it a reliable solution for real-world applications in domains like HAR.
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。
