Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent

TL;DR

This paper benchmarks recurrent event-based object detection models for industrial multi-class recognition using the MTevent dataset, analyzing the impact of temporal memory and pretraining methods.

Contribution

It provides a detailed benchmarking and analysis of recurrent versus non-recurrent models, highlighting the effects of pretraining and clip length in industrial scenarios.

Findings

Recurrent models outperform non-recurrent baselines by 9.6% in mAP50.

Event-domain pretraining improves detection performance and consistency.

Mismatched pretraining can be less effective than training from scratch.

Abstract

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.