TEAL：经验回放类别增量学习中面向小缓冲区的新型选择策略
TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental Learning
AI总结：
针对类别增量经验回放在小缓冲区下性能下降的问题，提出 TEAL 样本选择策略，优先保存典型数据，在每类仅 1-3 个样本时显著提升现有方法并达到最先进水平。
摘要：
持续学习是一个尚未解决的挑战，在现代应用中其重要性不断提升。与人脑不同，经过训练的深度神经网络会遭受一种称为灾难性遗忘的现象：在学习新任务时，它们会逐渐丧失先前获得的知识。为缓解这一问题，研究者已开发出许多方法，其中不少依赖于在新任务训练期间回放过去的样本。然而，随着分配给回放的内存减少，这些方法的有效性会下降。另一方面，为回放维护大型内存效率低下，而且往往不切实际。本文提出 TEAL，这是一种用样本填充内存的新方法，可与多种经验回放方法集成，并在内存缓冲区较小时显著提升其性能。我们表明，TEAL 提高了现有类别增量方法的平均准确率，并优于其他选择策略；即使在最终任务中每类仅使用 1-3 个样本的小型内存缓冲区，也能达到最先进性能。这证实了我们最初的假设：当内存稀缺时，最好优先选择最具代表性的数据。代码位于该 https URL：https://github.com/shahariel/TEAL。
英文摘要：
Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they progressively lose previously acquired knowledge upon learning new tasks. To mitigate this problem, numerous methods have been developed, many relying on the replay of past exemplars during new task training. However, as the memory allocated for replay decreases, the effectiveness of these approaches diminishes. On the other hand, maintaining a large memory for the purpose of replay is inefficient and often impractical. Here we introduce TEAL, a novel approach to populate the memory with exemplars, that can be integrated with various experience-replay methods and significantly enhance their performance with small memory buffers. We show that TEAL enhances the average accuracy of existing class-incremental methods and outperforms other selection strategies, achieving state-of-the-art performance even with small memory buffers of 1-3 exemplars per class in the final task. This confirms our initial hypothesis that when memory is scarce, it is best to prioritize the most typical data. Code is available at this https URL: https://github.com/shahariel/TEAL.
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。
