I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
It addresses a critical data bottleneck for neuromorphic engineering, enabling scalable SNN development with broad applications in energy-efficient computing.
The paper tackles the scarcity of event-stream data for spiking neural networks (SNNs) by introducing I2E, a framework that converts static images into event streams, achieving a 300x faster conversion speed and enabling SNNs to reach state-of-the-art accuracies of 60.50% on ImageNet and 92.5% on CIFAR10-DVS.
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.