论文标题
事件变压器。用于有效的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
论文作者
论文摘要
对于在低资源和挑战性环境中运行的许多应用程序，事件摄像机是引起人们兴趣的传感器。他们记录稀疏照明随时间分辨率和高动态范围的变化，同时呈现最少的功耗。但是，表现最佳的方法通常忽略了特定的事件数据属性，从而导致通用但计算上昂贵的算法的发展。为有效的解决方案努力通常无法为复杂的任务取得顶级准确的结果。这项工作提出了一个新颖的框架，即事件变压器（EVT），该框架有效地利用事件数据属性是高效和准确的。我们介绍了一个新的基于补丁的事件表示形式和一个紧凑的变压器样体系结构来处理它。 EVT对不同的基于事件的基准进行了评估，以进行动作和手势识别。评估结果表现出与最先进的精度更好或可比的，同时需要较少的计算资源，这使EVT能够在GPU和CPU上使用最小的延迟。
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.
