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.
@article{arxiv.2601.11640,
title = {Confident Learning for Object Detection under Model Constraints},
author = {Yingda Yu and Jiaqi Xuan and Shuhui Shi and Xuanyu Teng and Shuyang Xu and Guanchao Tong},
journal= {arXiv preprint arXiv:2601.11640},
year = {2026}
}