AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants

AYOLO introduces a novel fusion architecture that integrates unsupervised learning techniques with Vision Transformers, leveraging the YOLO series models as its foundation. This innovation enables the effective utilization of rich, unlabeled data, establishing a new pretraining methodology tailored...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Yılmaz, Yüksel Yurtay, Nilüfer Yurtay
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2718
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225247253430272
author Ali Yılmaz
Yüksel Yurtay
Nilüfer Yurtay
author_facet Ali Yılmaz
Yüksel Yurtay
Nilüfer Yurtay
author_sort Ali Yılmaz
collection DOAJ
description AYOLO introduces a novel fusion architecture that integrates unsupervised learning techniques with Vision Transformers, leveraging the YOLO series models as its foundation. This innovation enables the effective utilization of rich, unlabeled data, establishing a new pretraining methodology tailored to YOLO architectures. On a custom dataset comprising 80 images of poppy plants, AYOLO achieved a remarkable Average Precision (AP) of 38.7% while maintaining a high rendering speed of 239 FPS (Frames Per Second) on a Tesla K80 GPU. Real-time performance is demonstrated by achieving 239 FPS, and feature fusion optimally combines spatial and semantic information across scales. This performance surpasses the previous state-of-the-art YOLO v6-3.0 by +2.2% AP while retaining comparable speed. AYOLO exemplifies the potential of integrating advanced information fusion techniques with supervised pretraining, significantly enhancing precision and efficiency for object detection models optimized for small, specialized datasets.
format Article
id doaj-art-899d6684f6d344d39c3b71dfe86d867a
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-899d6684f6d344d39c3b71dfe86d867a2025-08-20T02:05:24ZengMDPI AGApplied Sciences2076-34172025-03-01155271810.3390/app15052718AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated PlantsAli Yılmaz0Yüksel Yurtay1Nilüfer Yurtay2Department of Computer Engineering, Sakarya University, Sakarya 54050, TurkeyDepartment of Computer Engineering, Sakarya University, Sakarya 54050, TurkeyDepartment of Computer Engineering, Sakarya University, Sakarya 54050, TurkeyAYOLO introduces a novel fusion architecture that integrates unsupervised learning techniques with Vision Transformers, leveraging the YOLO series models as its foundation. This innovation enables the effective utilization of rich, unlabeled data, establishing a new pretraining methodology tailored to YOLO architectures. On a custom dataset comprising 80 images of poppy plants, AYOLO achieved a remarkable Average Precision (AP) of 38.7% while maintaining a high rendering speed of 239 FPS (Frames Per Second) on a Tesla K80 GPU. Real-time performance is demonstrated by achieving 239 FPS, and feature fusion optimally combines spatial and semantic information across scales. This performance surpasses the previous state-of-the-art YOLO v6-3.0 by +2.2% AP while retaining comparable speed. AYOLO exemplifies the potential of integrating advanced information fusion techniques with supervised pretraining, significantly enhancing precision and efficiency for object detection models optimized for small, specialized datasets.https://www.mdpi.com/2076-3417/15/5/2718YOLO series algorithmsDETRarchitecturevision transformers (ViT)object detectionFPN (feature pyramid network)
spellingShingle Ali Yılmaz
Yüksel Yurtay
Nilüfer Yurtay
AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
Applied Sciences
YOLO series algorithms
DETR
architecture
vision transformers (ViT)
object detection
FPN (feature pyramid network)
title AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
title_full AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
title_fullStr AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
title_full_unstemmed AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
title_short AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
title_sort ayolo development of a real time object detection model for the detection of secretly cultivated plants
topic YOLO series algorithms
DETR
architecture
vision transformers (ViT)
object detection
FPN (feature pyramid network)
url https://www.mdpi.com/2076-3417/15/5/2718
work_keys_str_mv AT aliyılmaz ayolodevelopmentofarealtimeobjectdetectionmodelforthedetectionofsecretlycultivatedplants
AT yukselyurtay ayolodevelopmentofarealtimeobjectdetectionmodelforthedetectionofsecretlycultivatedplants
AT niluferyurtay ayolodevelopmentofarealtimeobjectdetectionmodelforthedetectionofsecretlycultivatedplants