发表机构
Rochester Institute of Technology（罗切斯特理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出基于生长自组织映射与合成重放的无监督持续学习框架，无需原始数据与监督信息，在多基准测试中性能优于无内存方法，在单类增量场景表现突出，为相关研究提供参考。
AI 中文摘要
本研究提出一种基于生长自组织映射（GSOMs）的生成式持续学习框架，该框架针对类增量学习任务，补充了学习到的分布统计量及编码器-解码器模型。所提方法利用分布统计内存实现无示例重放，无需存储原始数据；每个GSOM单元维护自身的均值、方差与协方差估计值，这些值随后被用于生成合成样本以进行重放；在编码器-解码器配置中，这些样本通过祖先采样解码回输入空间，用于后续训练。本方法完全无监督，训练期间不依赖显式任务边界或类别标签。多项基准测试结果显示，所提方法的性能可与基于内存的监督式最先进方法相媲美，且始终优于无内存方法；在若干场景中，本框架的表现与现有基准相当或更优，尤其在具挑战性的单类增量场景中。我们还提供了单类增量TinyImageNet与MiniImageNet的基准结果，为未来研究提供有用参考。本研究凸显了无监督、自适应、拓扑驱动的神经统计重放作为可扩展、灵活的持续学习方法的有效性。
英文摘要
This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input space (via ancestral sampling) for subsequent training. Our method is fully unsupervised, as it does not rely on explicit task boundaries or class labels during training. Results across multiple benchmarks show that the proposed approach achieves performance competitive even with supervised state-of-the-art memory-based methods while consistently outperforming memory-free approaches. In several settings, our framework matches or exceeds existing baselines, particularly in challenging single-class incremental scenarios. We also provide baseline results for single-class incremental TinyImageNet and MiniImageNet, offering a useful reference for future work. This work highlights the effectiveness of an unsupervised, adaptive, topology-driven neural form of statistical replay as a scalable, flexible approach to continual learning.
