Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn't available all at once, and the model must adapt to a new data distribution that may or may not follow the initial distribution. Previously acquired knowledge is lost during subsequent updates based on new data. a phenomenon commonly known as catastrophic forgetting. In contrast, the brain can learn without such catastrophic forgetting, irrespective of the number of tasks it encounters. Existing spiking neural networks (SNNs) for class-incremental learning (CIL) suffer a sharp performance drop as tasks accumulate. We here introduce CATFormer (Context Adaptive Threshold Transformer), a scalable framework that overcomes this limitation. We observe that the key to preventing forgetting in SNNs lies not only in synaptic plasticity but also in modulating neuronal excitability. At the core of CATFormer is the Dynamic Threshold Leaky Integrate-and-Fire (DTLIF) neuron model, which leverages context-adaptive thresholds as the primary mechanism for knowledge retention. This is paired with a Gated Dynamic Head Selection (G-DHS) mechanism for task-agnostic inference. Extensive evaluation on both static (CIFAR-10/100/Tiny-ImageNet) and neuromorphic (CIFAR10-DVS/SHD) datasets reveals that CATFormer outperforms existing rehearsal-free CIL algorithms across various task splits, establishing it as an ideal architecture for energy-efficient, true-class incremental learning.

翻译：尽管深度神经网络在受控环境中表现极佳，但在现实场景中却往往失效——这些场景中的数据并非一次性全部可得，且模型必须适应可能偏离初始分布的新数据分布。先前习得的知识在基于新数据的后续更新过程中会丢失，这一现象通常被称为灾难性遗忘。相比之下，大脑能够在不发生此类灾难性遗忘的情况下持续学习，无论其遇到的任务数量如何。现有的用于类增量学习（CIL）的脉冲神经网络（SNNs）随着任务累积会出现性能急剧下降的问题。本文提出CATFormer（上下文自适应阈值Transformer），一个可扩展的框架以克服这一局限。我们发现，在SNNs中防止遗忘的关键不仅在于突触可塑性，还在于调节神经元兴奋性。CATFormer的核心是动态阈值泄漏积分发放（DTLIF）神经元模型，该模型利用上下文自适应阈值作为知识保留的主要机制。该模型与门控动态头部选择（G-DHS）机制相结合，实现任务无关的推理。在静态数据集（CIFAR-10/100/Tiny-ImageNet）和神经形态数据集（CIFAR10-DVS/SHD）上的广泛评估表明，CATFormer在各种任务划分下均优于现有的无排练CIL算法，从而确立了其作为高能效、真实类增量学习的理想架构地位。