# DBA-YOLO: A Dense Target Detection Model Based on Lightweight Neural Networks

## TL;DR

DBA-YOLO is a lightweight model for detecting dense targets in industrial settings, offering high accuracy and efficiency on mobile devices.

## Contribution

The paper introduces DBA-YOLO, a novel lightweight detection model with improved modules for dense target detection and reduced computational complexity.

## Key findings

- DBA-YOLO achieves 91.3% detection accuracy, outperforming the baseline by 1.4%.
- The model improves mAP and mAP75 by 2–3% while reducing parameters by 3.6%.
- Experiments on SKU-110K and a cigarette package dataset validate its effectiveness in real-world scenarios.

## Abstract

Current deep learning-based dense target detection models face dual challenges in industrial scenarios: high computational complexity leading to insufficient inference efficiency on mobile devices, and missed/false detections caused by dense small targets, high inter-class similarity, and complex background interference. To address these issues, this paper proposes DBA-YOLO, a lightweight model based on YOLOv10, which significantly reduces computational complexity through model compression and algorithm optimization while maintaining high accuracy. Key improvements include the following: (1) a C2f PA module for enhanced feature extraction, (2) a parameter-refined BIMAFPN neck structure to improve small target detection, and (3) a DyDHead module integrating scale, space, and task awareness for spatial feature weighting. To validate DBA-YOLO, we constructed a real-world dataset from cigarette package images. Experiments on SKU-110K and our dataset show that DBA-YOLO achieves 91.3% detection accuracy (1.4% higher than baseline), with mAP and mAP75 improvements of 2–3%. Additionally, the model reduces parameters by 3.6%, balancing efficiency and performance for resource-constrained devices.