发表机构
CNRS; INSA Lyon（法国国家科学研究中心; 里昂国立应用科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究将二值神经网络适配于事件相机数据，提出极性二值事件体（PBEV）表示，实现直接处理，并在N-Caltech101上以7.5倍运算量减少达到90.58%准确率，展示了高效事件视觉系统的潜力。
AI 中文摘要
二值神经网络（BNNs）通过将权重和激活压缩至一位，使得深度学习能够在资源受限的设备上高效部署，大幅减少模型大小和推理成本。事件相机通过捕捉异步事件流而非密集图像帧，提供了互补的优势，包括低延迟、高动态范围和低功耗。尽管两者都强调效率，但将这些技术相结合的研究仍然在很大程度上未被探索。本研究旨在将现代深度二值神经网络架构适配并评估于事件数据上。我们还展示了从RGB数据进行跨模态预训练可以提高二值神经网络在神经形态数据集上的分类准确率。我们引入了极性二值事件体（PBEV），这是一种二值表示，使得事件相机数据能够直接被二值神经网络处理，并代表了迈向全二值化事件视觉系统的一步。在N-Caltech101分类基准上评估的最佳二值神经网络达到了90.58%的准确率，同时其运算量比全精度对应网络少7.5倍。
英文摘要
Binary Neural Networks (BNNs) enable efficient deep learning deployment on resource constrained devices with weights and activations compressed to one bit, substantially reducing model size and inference cost. Event cameras offer complementary advantages, including low latency, high dynamic range, and low power consumption, by capturing asynchronous streams of events rather than dense image frames. Despite their shared emphasis on efficiency, the combination of these technologies remains largely unexplored. This work aims at adapting and evaluating modern deep BNN architectures on event data. We also show that cross-modal pretraining from RGB data can improve the classification accuracy of BNNs on neuromorphic datasets. We introduce the Polar-wise Binary Event Volume (PBEV), a binary representation that enables event-camera data to be processed directly by BNNs and represents a step toward fully binarized event-based vision systems. Best evaluated BNN on N-Caltech101 classification benchmarks shows 90.58% accuracy with 7.5x less operations than their full-precision counterparts.
Comments19 pages, 3 figures, 8 tables. Accepted by NeVi Workshop at ECCV 2026
