Closing the Accuracy Gap in an Event-Based Visual Recognition Task
Closing the Accuracy Gap in an Event-Based Visual Recognition Task
复制标题
缩小基于事件的视觉识别任务中的准确度差距
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Yulia Sandamirskaya
中科院分区：
文献类型：
--
作者：
Bodo Rückauer;Nicolas Känzig;Shih;T. Delbrück;Yulia Sandamirskaya
移动的和嵌入式应用需要基于神经网络的模式识别系统在紧张的计算预算下表现良好。与常用的同步、基于帧的视觉系统和CNN相反，由基于事件的视觉输入驱动的异步、尖峰神经网络以低延迟响应输入中的稀疏、显著特征，从而在运行时实现高效率。基于事件的数据流的离散性使得异步神经网络的直接训练具有挑战性。本文研究了异步脉冲神经网络，通过转换从基于帧的数据训练的传统CNN获得。作为一个例子，我们考虑一个CNN训练，以引导机器人跟随移动目标。我们确定了转换的可能陷阱，并演示了所提出的解决方案如何使异步网络的分类精度仅低于原始同步CNN的性能的3%，同时需要减少12倍的计算。虽然被应用于一个简单的任务，这项工作是一个重要的一步，为机器人应用低功耗，快速，嵌入式基于神经网络的视觉解决方案。
Mobile and embedded applications require neural networks-based pattern recognition systems to perform well under a tight computational budget. In contrast to commonly used synchronous, frame-based vision systems and CNNs, asynchronous, spiking neural networks driven by event-based visual input respond with low latency to sparse, salient features in the input, leading to high efficiency at run-time. The discrete nature of the event-based data streams makes direct training of asynchronous neural networks challenging. This paper studies asynchronous spiking neural networks, obtained by conversion from a conventional CNN trained on frame-based data. As an example, we consider a CNN trained to steer a robot to follow a moving target. We identify possible pitfalls of the conversion and demonstrate how the proposed solutions bring the classification accuracy of the asynchronous network to only 3\% below the performance of the original synchronous CNN, while requiring 12x fewer computations. While being applied to a simple task, this work is an important step towards low-power, fast, and embedded neural networks-based vision solutions for robotic applications.