I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Classification | CIFAR10-DVS | Accuracy92.5 | 78 | |
| Image Classification | ImageNet-ES (test) | -- | 12 | |
| Image Classification | I2E-ImageNet (test) | Accuracy60.5 | 4 | |
| Image Classification | N-ImageNet (test) | -- | 4 | |
| Image Classification | CIFAR10 I2E | Accuracy (CIFAR-10 I2E)90.86 | 3 | |
| Image Classification | I2E-CIFAR100 | Accuracy64.53 | 3 | |
| Event-based Dataset Generation | I2E-CIFAR10 | Generation Speed (ms/sample)0.03 | 1 | |
| Event-based Dataset Generation | CIFAR100 I2E | Generation Latency (ms/sample)0.03 | 1 | |
| Event-based Dataset Generation | ImageNet I2E | Generation Speed (ms/sample)0.1 | 1 | |
| Event-based Dataset Generation | N-Cars | -- | 1 |