在工业场景下对比循环事件相机目标检测模型性能，发现时序记忆提升识别准确率。
Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent
- 采用循环ReYOLOv8s与非循环基线对比，引入时序记忆建模
- 最佳模型达到0.329 mAP50，相比基线提升15.0%（0.260→0.329）
- 事件域预训练显著提升性能，但源域不匹配会降低效果
事件相机因其高时间分辨率、高动态范围和低运动模糊，适用于工业机器人。然而，现有事件相机目标检测研究多聚焦于室外驾驶场景或少数类别。本文在工业多类识别数据集MTevent上，对循环式ReYOLOv8s进行基准测试，并以非循环YOLOv8s为基线，分析时序记忆的影响。在MTevent验证集上，最佳从头训练的循环模型（C21）达到0.285 mAP50，较非循环基线（0.260）相对提升9.6%。事件域预训练效果更优：使用GEN1初始化微调，在片段长度21时取得最高0.329 mAP50，且性能随片段长度持续提升；而PEDRo初始化降至0.251，表明源域不匹配的预训练可能不如从头训练。持久性失败模式主要由类别不平衡和人-物体交互导致。本工作定位为工业环境中循环事件检测的系统性基准与分析。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。