YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection

Effective weed management is essential for protecting crop yields in cotton production, yet conventional deep learning approaches often falter in detecting small or occluded weeds and can be restricted by large parameter counts. To tackle these challenges, we propose YOLO-ACE, an advanced extension...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Zhou, Huicheng Li, Zhiling Cai, Yiwen Zhong, Fenglin Zhong, Xiaoyu Lin, Lijin Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1635
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031502724694016
author Qi Zhou
Huicheng Li
Zhiling Cai
Yiwen Zhong
Fenglin Zhong
Xiaoyu Lin
Lijin Wang
author_facet Qi Zhou
Huicheng Li
Zhiling Cai
Yiwen Zhong
Fenglin Zhong
Xiaoyu Lin
Lijin Wang
author_sort Qi Zhou
collection DOAJ
description Effective weed management is essential for protecting crop yields in cotton production, yet conventional deep learning approaches often falter in detecting small or occluded weeds and can be restricted by large parameter counts. To tackle these challenges, we propose YOLO-ACE, an advanced extension of YOLOv5s, which was selected for its optimal balance of accuracy and speed, making it well suited for agricultural applications. YOLO-ACE integrates a Context Augmentation Module (CAM) and Selective Kernel Attention (SKAttention) to capture multi-scale features and dynamically adjust the receptive field, while a decoupled detection head separates classification from bounding box regression, enhancing overall efficiency. Experiments on the CottonWeedDet12 (CWD12) dataset show that YOLO-ACE achieves notable mAP@0.5 and mAP@0.5:0.95 scores—95.3% and 89.5%, respectively—surpassing previous benchmarks. Additionally, we tested the model’s transferability and generalization across different crops and environments using the CropWeed dataset, where it achieved a competitive mAP@0.5 of 84.3%, further showcasing its robust ability to adapt to diverse conditions. These results confirm that YOLO-ACE combines precise detection with parameter efficiency, meeting the exacting demands of modern cotton weed management.
format Article
id doaj-art-9d80205870b84059b6f00a035d57743f
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-9d80205870b84059b6f00a035d57743f2025-08-20T02:58:57ZengMDPI AGSensors1424-82202025-03-01255163510.3390/s25051635YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed DetectionQi Zhou0Huicheng Li1Zhiling Cai2Yiwen Zhong3Fenglin Zhong4Xiaoyu Lin5Lijin Wang6College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaCollege of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, ChinaEffective weed management is essential for protecting crop yields in cotton production, yet conventional deep learning approaches often falter in detecting small or occluded weeds and can be restricted by large parameter counts. To tackle these challenges, we propose YOLO-ACE, an advanced extension of YOLOv5s, which was selected for its optimal balance of accuracy and speed, making it well suited for agricultural applications. YOLO-ACE integrates a Context Augmentation Module (CAM) and Selective Kernel Attention (SKAttention) to capture multi-scale features and dynamically adjust the receptive field, while a decoupled detection head separates classification from bounding box regression, enhancing overall efficiency. Experiments on the CottonWeedDet12 (CWD12) dataset show that YOLO-ACE achieves notable mAP@0.5 and mAP@0.5:0.95 scores—95.3% and 89.5%, respectively—surpassing previous benchmarks. Additionally, we tested the model’s transferability and generalization across different crops and environments using the CropWeed dataset, where it achieved a competitive mAP@0.5 of 84.3%, further showcasing its robust ability to adapt to diverse conditions. These results confirm that YOLO-ACE combines precise detection with parameter efficiency, meeting the exacting demands of modern cotton weed management.https://www.mdpi.com/1424-8220/25/5/1635weed detectiondeep learningYOLOv5sattention mechanism
spellingShingle Qi Zhou
Huicheng Li
Zhiling Cai
Yiwen Zhong
Fenglin Zhong
Xiaoyu Lin
Lijin Wang
YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
Sensors
weed detection
deep learning
YOLOv5s
attention mechanism
title YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
title_full YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
title_fullStr YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
title_full_unstemmed YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
title_short YOLO-ACE: Enhancing YOLO with Augmented Contextual Efficiency for Precision Cotton Weed Detection
title_sort yolo ace enhancing yolo with augmented contextual efficiency for precision cotton weed detection
topic weed detection
deep learning
YOLOv5s
attention mechanism
url https://www.mdpi.com/1424-8220/25/5/1635
work_keys_str_mv AT qizhou yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT huichengli yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT zhilingcai yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT yiwenzhong yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT fenglinzhong yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT xiaoyulin yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection
AT lijinwang yoloaceenhancingyolowithaugmentedcontextualefficiencyforprecisioncottonweeddetection