Confident Learning for Object Detection under Model Constraints

TL;DR

This paper introduces Model-Driven Data Correction (MDDC), a data-centric approach that improves object detection performance on edge devices by diagnosing and fixing data quality issues without increasing model complexity.

Contribution

The paper presents a novel data correction framework that systematically diagnoses and addresses detection errors, enhancing performance under strict model and resource constraints.

Findings

Achieved 5-25% mAP improvement on weed detection datasets.

Demonstrated effectiveness of data correction in resource-constrained environments.

Validated approach with consistent gains across multiple datasets.

Abstract

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.