在MTevent上评估用于工业多类识别的循环事件基目标检测基准
Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent
AI总结：
本文研究了在MTevent数据集上使用循环ReYOLOv8s进行工业多类识别的性能，并通过非循环YOLOv8s作为基线分析时间记忆的影响，发现事件域预训练对性能提升更有效。
摘要：
事件相机因提供高时间分辨率、高动态范围和减少运动模糊而在工业机器人中具有吸引力。然而，大多数基于事件的目标检测研究集中在户外驾驶场景或有限类别设置上。在本工作中，我们在MTevent上评估了循环ReYOLOv8s用于工业多类识别，并使用非循环YOLOv8s变体作为基线来分析时间记忆的影响。在MTevent验证分割上，最佳的从头开始的循环模型（C21）达到了0.285 mAP50，比非循环YOLOv8s基线（0.260）提高了9.6%。事件域预训练效果更显著：GEN1初始化的微调在剪辑长度21时达到了最佳整体结果0.329 mAP50，并且与从头开始训练不同，GEN1预训练模型在剪辑长度上持续改进。PEDRo初始化下降到0.251，表明源域预训练不匹配可能不如从头开始训练有效。持续失败模式主要由类别不平衡和人-物体交互主导。总体而言，我们将这项工作定位为对工业环境中循环事件基检测的聚焦基准测试和分析研究。
英文摘要：
Event cameras are attractive for industrial robotics because they provide high temporal resolution, high dynamic range, and reduced motion blur. However, most event-based object detection studies focus on outdoor driving scenarios or limited class settings. In this work, we benchmark recurrent ReYOLOv8s on MTevent for industrial multi-class recognition and use a non-recurrent YOLOv8s variant as a baseline to analyze the effect of temporal memory. On the MTevent validation split, the best scratch recurrent model (C21) reaches 0.285 mAP50, corresponding to a 9.6\% relative improvement over the non-recurrent YOLOv8s baseline (0.260). Event-domain pretraining has a stronger effect: GEN1-initialized fine-tuning yields the best overall result of 0.329 mAP50 at clip length 21, and unlike scratch training, GEN1-pretrained models improve consistently with clip length. PEDRo initialization drops to 0.251, indicating that mismatched source-domain pretraining can be less effective than training from scratch. Persistent failure modes are dominated by class imbalance and human-object interaction. Overall, we position this work as a focused benchmarking and analysis study of recurrent event-based detection in industrial environments.
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。
