基于自组织映射和合成重放的类别增量持续学习
Class Incremental Continual Learning with Self-Organizing Maps and Synthetic Replay
AI总结：
该研究提出基于自组织映射（SOM）与合成重放的类别增量持续学习框架，在多基准数据集上性能优于无内存方法，为类别增量持续学习提供了可扩展的无标签无示例方案。
摘要：
本研究提出一种新颖的生成式持续学习框架，该框架基于受大脑启发的自然计算模型——自组织映射（Self-Organizing Maps, SOM）构建，扩展了学习到的分布统计量与编码器-解码器模型，用于类别增量持续学习。这些扩展后的SOM支持使用固定容量统计内存的无示例重放，无需存储原始数据样本。对于高维输入空间，SOM在编码器-解码器的潜在空间中运行；对于低维输入，则以独立方式运行。我们的方法为每个SOM单元存储运行均值、方差和协方差，后续学习迭代中可基于这些统计量生成合成样本。对于编码器-解码器方法，生成的样本会经过解码器处理，用于后续重放。在标准类别增量基准上的实验结果显示，我们的方法与最先进的基于内存的方法表现相当，且优于无内存方法；值得注意的是，在未使用预训练编码器的情况下，我们的方法在CIFAR-10和CIFAR-100上的最佳单类别增量性能，分别比现有最先进方法提升了近10%和7%。我们还在使用基础编码器-解码器的单类别增量CIFAR-100上取得了最佳性能，并首次给出了单类别增量TinyImageNet的基准结果。我们的方法便于学习过程的可视化，训练完成后也可作为生成模型使用。总体而言，结果表明基于SOM的统计重放为标准任务边界协议下的类别增量持续学习提供了一种可扩展、无标签、无示例的方法。
英文摘要：
This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs), a brain-inspired natural computing model, extended with learned distributional statistics and encoder--decoder models for class incremental continual learning. These extended SOMs enable exemplar-free replay with fixed-capacity statistical memory, eliminating the need to store raw data samples. For high-dimensional input spaces, the SOM operates over the latent space of the encoder--decoder, while for lower-dimensional inputs, the SOM operates in a standalone fashion. Our method stores a running mean, variance, and covariance for each SOM unit, from which synthetic samples are then generated during future learning iterations. For the encoder--decoder method, generated samples are fed through the decoder to be used in subsequent replay. Experimental results on standard class-incremental benchmarks show that our approach performs competitively with state-of-the-art memory-based methods and outperforms memory-free methods, notably improving over the best state-of-the-art single-class incremental performance without pretrained encoders on CIFAR-10 and CIFAR-100 by nearly 10% and 7%, respectively. We also achieve the best performance on single-class incremental CIFAR-100 using a foundational encoder-decoder and present the first baseline results for single-class incremental TinyImageNet. Our methodology facilitates easy visualization of the learning process and can also be utilized as a generative model post-training. Overall, the results demonstrate that SOM-based statistical replay offers a scalable, label-free, exemplar-free approach to class-incremental continual learning under standard task-boundary protocols.
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。
