将静态图像转为事件流，加速脉冲神经网络训练。
I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
- 模拟微扫视眼动，用并行卷积快速生成事件流。
- 在ImageNet上训练的SNN达60.50%准确率，超越现有水平。
- 合成数据预训练+真实数据微调，实现92.5%高精度。
脉冲神经网络（SNN）具备极低功耗计算潜力，但其应用受限于事件流数据的严重短缺。本文提出I2E算法框架，通过模拟微扫视眼动的并行卷积，将静态图像高效转换为高保真事件流，转换速度较此前方法提升300倍以上，首次实现SNN训练中的实时数据增强。在大规模基准测试中验证了该框架的有效性：基于生成的I2E-ImageNet数据集训练的SNN达到60.50%的领先准确率。关键突破在于，采用合成I2E数据预训练、真实世界CIFAR10-DVS数据微调的“仿真到现实”范式，实现92.5%的前所未有的准确率。该结果证明合成事件数据可作为真实传感器数据的高质量代理，弥合了类脑工程领域长期存在的数据鸿沟。I2E提供了一套可扩展的数据解决方案，为构建高性能类脑系统奠定基础。算法与全部生成数据集开源，以推动该领域研究发展。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This work introduces I2E, an algorithmic framework that resolves this bottleneck by converting static images into high-fidelity event streams. By simulating microsaccadic eye movements with a highly parallelized convolution, I2E achieves a conversion speed over 300x faster than prior methods, uniquely enabling on-the-fly data augmentation for SNN training. The framework's effectiveness is demonstrated on large-scale benchmarks. An SNN trained on the generated I2E-ImageNet dataset achieves a state-of-the-art accuracy of 60.50%. Critically, this work establishes a powerful sim-to-real paradigm where pre-training on synthetic I2E data and fine-tuning on the real-world CIFAR10-DVS dataset yields an unprecedented accuracy of 92.5%. This result validates that synthetic event data can serve as a high-fidelity proxy for real sensor data, bridging a long-standing gap in neuromorphic engineering. By providing a scalable solution to the data problem, I2E offers a foundational toolkit for developing high-performance neuromorphic systems. The open-source algorithm and all generated datasets are provided to accelerate research in the field.
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。