Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces

Abstract Recently, deep learning has been widely used in the field of Chinese Medicinal Decoction Pieces (CMDP) detection to address the limitations of inefficiency and subjectivity of professionals. However, deep learning networks typically require a large amount of data for training, and it is dif...

Full description

Saved in:
Bibliographic Details
Main Authors: Kai Hu, Chu-he Lin, Xing Jin, Hangjuan Lin
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00232-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225824738213888
author Kai Hu
Chu-he Lin
Xing Jin
Hangjuan Lin
author_facet Kai Hu
Chu-he Lin
Xing Jin
Hangjuan Lin
author_sort Kai Hu
collection DOAJ
description Abstract Recently, deep learning has been widely used in the field of Chinese Medicinal Decoction Pieces (CMDP) detection to address the limitations of inefficiency and subjectivity of professionals. However, deep learning networks typically require a large amount of data for training, and it is difficult to collect a large amount of labeled data for thousands of CMDP. This study aims to tackle the challenges posed by limited data availability in the context of CMDP detection. We propose Meta-YOLOv8, a novel few-shot object detection network based on YOLOv8. To effectively integrate YOLOv8 with meta-learning, we introduce three key modules: (i) Multi-Scale Class Feature Extraction Module (CFEM), (ii) Heterogeneous Graph Convolutional Networks (HGCN), and (iii) Multi-Scale Classification Auxiliary Module (CAM). The CFEM extracts high-quality class features at each scale through Task Alignment Learning. The HGCN facilitates context information enhancement and cross-sample information sharing via intra-scale subgraphs and learns intrinsic connections across scales using inter-scale subgraphs to create scale-specific class prototypes. Finally, the CAM leverages these scale-specific class prototypes to support multi-scale classification. We tested the proposed Meta-YOLOv8 model on two common image datasets, VOC and COCO, as well as a self-built CMDP image dataset. Compared to other few-shot object detection approaches, our proposed model achieves competitive results. Compared to YOLOv8, our method improves the mean average precision ( $$mAP_{0.5}$$ m A P 0.5 ) by 2.2% to 20.4% in different settings, with only a marginal increase in the inference time of 6.6%. The proposed approach integrates meta-learning with YOLOv8, enabling accurate identification of novel CMDPs with only a small number of samples. This capability significantly enhances the efficiency and feasibility of CMDP detection, thereby providing strong technical support for the smart development of the Traditional Chinese Medicine (TCM) industry.
format Article
id doaj-art-308f98d01ce149a3a06112e0f277bfb0
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-308f98d01ce149a3a06112e0f277bfb02025-08-24T11:53:39ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137711910.1007/s44443-025-00232-xMeta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction piecesKai Hu0Chu-he Lin1Xing Jin2Hangjuan Lin3Department of Pharmacy, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical UniversityFaculty of Electrical Engineering and Computer Science, Ningbo UniversityFaculty of Electrical Engineering and Computer Science, Ningbo UniversityDepartment of Pharmacy, Ningbo Municipal Hospital of Traditional Chinese Medicine (TCM), Affiliated Hospital of Zhejiang Chinese Medical UniversityAbstract Recently, deep learning has been widely used in the field of Chinese Medicinal Decoction Pieces (CMDP) detection to address the limitations of inefficiency and subjectivity of professionals. However, deep learning networks typically require a large amount of data for training, and it is difficult to collect a large amount of labeled data for thousands of CMDP. This study aims to tackle the challenges posed by limited data availability in the context of CMDP detection. We propose Meta-YOLOv8, a novel few-shot object detection network based on YOLOv8. To effectively integrate YOLOv8 with meta-learning, we introduce three key modules: (i) Multi-Scale Class Feature Extraction Module (CFEM), (ii) Heterogeneous Graph Convolutional Networks (HGCN), and (iii) Multi-Scale Classification Auxiliary Module (CAM). The CFEM extracts high-quality class features at each scale through Task Alignment Learning. The HGCN facilitates context information enhancement and cross-sample information sharing via intra-scale subgraphs and learns intrinsic connections across scales using inter-scale subgraphs to create scale-specific class prototypes. Finally, the CAM leverages these scale-specific class prototypes to support multi-scale classification. We tested the proposed Meta-YOLOv8 model on two common image datasets, VOC and COCO, as well as a self-built CMDP image dataset. Compared to other few-shot object detection approaches, our proposed model achieves competitive results. Compared to YOLOv8, our method improves the mean average precision ( $$mAP_{0.5}$$ m A P 0.5 ) by 2.2% to 20.4% in different settings, with only a marginal increase in the inference time of 6.6%. The proposed approach integrates meta-learning with YOLOv8, enabling accurate identification of novel CMDPs with only a small number of samples. This capability significantly enhances the efficiency and feasibility of CMDP detection, thereby providing strong technical support for the smart development of the Traditional Chinese Medicine (TCM) industry.https://doi.org/10.1007/s44443-025-00232-xFew-shot object detectionMeta-learningYOLOv8Chinese medicinal decoction pieces
spellingShingle Kai Hu
Chu-he Lin
Xing Jin
Hangjuan Lin
Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
Journal of King Saud University: Computer and Information Sciences
Few-shot object detection
Meta-learning
YOLOv8
Chinese medicinal decoction pieces
title Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
title_full Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
title_fullStr Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
title_full_unstemmed Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
title_short Meta-YOLOv8: multi-scale few-shot object detection for Chinese medicinal decoction pieces
title_sort meta yolov8 multi scale few shot object detection for chinese medicinal decoction pieces
topic Few-shot object detection
Meta-learning
YOLOv8
Chinese medicinal decoction pieces
url https://doi.org/10.1007/s44443-025-00232-x
work_keys_str_mv AT kaihu metayolov8multiscalefewshotobjectdetectionforchinesemedicinaldecoctionpieces
AT chuhelin metayolov8multiscalefewshotobjectdetectionforchinesemedicinaldecoctionpieces
AT xingjin metayolov8multiscalefewshotobjectdetectionforchinesemedicinaldecoctionpieces
AT hangjuanlin metayolov8multiscalefewshotobjectdetectionforchinesemedicinaldecoctionpieces