在模型容量受限下，通过数据纠错提升农业杂草检测精度。
Confident Learning for Object Detection under Model Constraints
- 基于模型诊断错误类型，迭代修正数据质量问题。
- 固定轻量模型下mAP提升5%-25%。
- 适合边缘设备上资源受限的检测任务优化。
边缘设备上的农业杂草检测受模型容量、计算资源和实时推理延迟的严格限制，无法通过模型扩容或集成提升性能。本文提出模型驱动的数据修正（MDDC）框架，通过迭代诊断和修正数据质量缺陷来增强检测性能。自动化的错误分析将检测失败分为四类：漏检、误检、类别混淆和定位误差。这些错误模式通过结构化的训练-修正-重训练流程系统性解决，并配合版本化数据管理。在多个杂草检测数据集上的实验表明，在固定轻量级检测器YOLOv8n条件下，[email protected]提升5%-25%，证明在模型容量不变时，系统性数据质量优化可有效缓解性能瓶颈。
原文摘要 · Abstract (English)
Agricultural weed detection on edge devices is subject to strict constraints on model capacity, computational resources, and real-time inference latency, which prevent performance improvements through model scaling or ensembling. This paper proposes Model-Driven Data Correction (MDDC), a data-centric framework that enhances detection performance by iteratively diagnosing and correcting data quality deficiencies. An automated error analysis procedure categorizes detection failures into four types: false negatives, false positives, class confusion, and localization errors. These error patterns are systematically addressed through a structured train-fix-retrain pipeline with version-controlled data management. Experimental results on multiple weed detection datasets demonstrate consistent improvements of 5-25 percent in mAP at 0.5 using a fixed lightweight detector (YOLOv8n), indicating that systematic data quality optimization can effectively alleviate performance bottlenecks under fixed model capacity constraints.
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。