提出轻量级框架sLoTh，让稀疏事件神经网络持续学习不丢旧知识。
Parameter Efficient Continual Learning for Sparse Event-Based Transformers
- 只更新少于1%参数，通过低秩注意力和阈值调节实现高效适应
- 在100个任务上性能媲美带重放的模型，能耗降低6.5倍
- 适合边缘设备部署，尤其适用于动态环境下的实时智能系统
机器人与边缘智能系统在动态环境中运行，数据持续输入，要求模型在严格内存与能耗限制下持续学习并保留已有知识。尽管参数高效微调在视觉变压器的持续学习中表现良好，但传统架构依赖密集计算，难以实际部署。稀疏事件驱动的视觉变压器虽具能效优势，但其持续学习能力尚未深入探索。本文提出sLoTh，一种针对预训练稀疏事件（脉冲）视觉变压器的参数高效持续学习框架。sLoTh冻结主干网络，仅对可扩展高效的低秩注意力更新（seLoRA）和共享神经元阈值调节进行可塑性调整，无需重放缓冲区即可更新不足1%的模型参数。在CIFAR-100、Tiny-ImageNet、ImageNet-100和ImageNet-R上，最多支持100个任务的类增量学习与在线持续学习实验表明，其性能在无重放条件下具有竞争力，同时相比传统密集视觉变压器实现约6.5倍的能效提升。
原文摘要 · Abstract (English)
Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict memory and energy constraints. While parameter-efficient fine-tuning has shown promise for continual learning with vision transformers, conventional architectures rely on dense computation and remain costly for real-world deployment. Sparse event-based vision transformers provide energy-efficient event-driven computation, yet their continual learning capabilities remain largely unexplored. We here introduce sLoTh, a parameter-efficient continual learning framework for pretrained sparse event-based (spiking) vision transformers. sLoTh freezes the backbone and restricts plasticity to scalable-efficient low-rank attention updates (seLoRA) and shared neuronal threshold modulation, enabling adaptation without replay buffers by updating less than 1% of model parameters. Experiments across CIFAR-100, Tiny-ImageNet, ImageNet-100, and ImageNet-R with up to 100 tasks demonstrate competitive rehearsal-free performance in class-incremental learning and online continual learning, while enabling approximately 6.5x lower energy consumption than conventional dense vision transformers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。