arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03355cs.CV
收藏

事件Transformer。用于高效事件数据处理的稀疏感知解决方案

Event Transformer. A sparse-aware solution for efficient event data processing

Universidad de Zaragoza(萨拉戈萨大学);Bitbrain Technologies(比特布莱恩科技公司)

Alberto Sabater, Luis Montesano, Ana C. Murillo

摘要:

事件摄像机是许多在低资源和挑战性环境中运行的应用程序非常感兴趣的传感器。它们记录稀疏照明变化,具有高时间分辨率和高动态范围,同时它们呈现最小的功耗。然而,性能最好的方法往往忽略特定的事件数据属性,导致通用的,但计算昂贵的算法的发展。对于复杂的任务,努力寻求有效的解决方案通常无法实现最高精度的结果。这项工作提出了一种新的框架,事件Transformer(EvT),有效地利用事件数据属性是高效和准确的。我们引入了一个新的基于补丁的事件表示和一个紧凑的transformer-like架构来处理它。EvT是在不同的动作和手势识别基于事件的基准进行评估。评估结果显示,EvT的准确性优于或相当于最先进的水平,同时需要的计算资源显著减少,这使得EvT能够在GPU和CPU上以最小的延迟工作。

英文摘要:

Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption. However, top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms. Efforts toward efficient solutions usually do not achieve top-accuracy results for complex tasks. This work proposes a novel framework, Event Transformer (EvT), that effectively takes advantage of event-data properties to be highly efficient and accurate. We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition. Evaluation results show better or comparable accuracy to the state-of-the-art while requiring significantly less computation resources, which makes EvT able to work with minimal latency both on GPU and CPU.

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。

↑