I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909897995583488 |
|---|---|
| author | Ma, Ruichen Meng, Liwei Qiao, Guanchao Ning, Ning Liu, Yang Hu, Shaogang |
| author_facet | Ma, Ruichen Meng, Liwei Qiao, Guanchao Ning, Ning Liu, Yang Hu, Shaogang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks Ma, Ruichen Meng, Liwei Qiao, Guanchao Ning, Ning Liu, Yang Hu, Shaogang Computer Vision and Pattern Recognition 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. |
| title | I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.08065 |