arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1508.01176cs.CV
收藏

HFirst:一种基于时间的目标识别方法

HFirst: A Temporal Approach to Object Recognition

National University of Singapore(新加坡国立大学);Singapore Institute for Neurotechnology (SINAPSE)(新加坡神经技术研究所(SINAPSE));Universite Pierre et Marie Curie(皮埃尔和玛丽·居里大学);Institut De la Vision(视觉研究所);Johns Hopkins University(约翰斯·霍普金斯大学)

Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, Ryad Benosman

摘要:

本文介绍了一个尖峰层次模型的对象识别,利用精确的定时信息固有的生物启发异步地址事件表示(AER)视觉传感器的输出。这些系统的异步性质将计算和通信从由常规系统中的系统时钟强制执行的刚性预定定时中解放出来。从严格的时间限制的自由开放的可能性,使用真正的时间,我们的优势,在计算。我们不仅展示了如何在对象识别中使用定时,而且还展示了它实际上如何简化计算。具体来说,我们依赖于一个简单的时间赢家通吃,而不是更多的计算密集型同步操作通常用于生物启发的神经网络的对象识别。这种视觉计算的方法代表了传统计时系统的一个主要范式转变,可以在其他感觉方式和计算任务中找到应用。我们展示了有效性的方法,实现了最高的准确率(97.5\% $\pm$ 3.5\%),为以前公布的四类卡点识别任务和准确率为84.9\% $\pm$ 1.9\%的一个新的更困难的36类字符识别任务。

英文摘要:

This paper introduces a spiking hierarchical model for object recognition which utilizes the precise timing information inherently present in the output of biologically inspired asynchronous Address Event Representation (AER) vision sensors. The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems. Freedom from rigid timing constraints opens the possibility of using true timing to our advantage in computation. We show not only how timing can be used in object recognition, but also how it can in fact simplify computation. Specifically, we rely on a simple temporal-winner-take-all rather than more computationally intensive synchronous operations typically used in biologically inspired neural networks for object recognition. This approach to visual computation represents a major paradigm shift from conventional clocked systems and can find application in other sensory modalities and computational tasks. We showcase effectiveness of the approach by achieving the highest reported accuracy to date (97.5\%$\pm$3.5\%) for a previously published four class card pip recognition task and an accuracy of 84.9\%$\pm$1.9\% for a new more difficult 36 class character recognition task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑