Spike-EVPR: Deep Spiking Residual Networks with SNN-Tailored Representations for Event-Based Visual Place Recognition
Spike-EVPR:基于事件视觉地点识别的深度脉冲残差网络
机构 * Faculty of Robot Science and Engineering, Northeastern University(机器人科学与工程学院,东北大学) ; School of Artificial Intelligence and Robotics, Hunan University(人工智能与机器人学院,湖南大学)
AI总结 Spike-EVPR通过引入两种互补的事件表示和深度脉冲残差架构,实现了高效的事件视觉地点识别,提升了召回率并降低了能耗。
Comments 8 pages, 6 figures