Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multi-Dimensional Resources Management with GNN for Adaptive Routing Optimization.

Sensors (Basel, Switzerland)·2026

Same author

DuSAFNet: A Multi-Path Feature Fusion and Spectral-Temporal Attention-Based Model for Bird Audio Classification.

Animals : an open access journal from MDPI·2025

Same author

LSD-YOLO: Enhanced YOLOv8n Algorithm for Efficient Detection of Lemon Surface Diseases.

Plants (Basel, Switzerland)·2024

Same author

Hyperspectral and Fluorescence Imaging Approaches for Nondestructive Detection of Rice Chlorophyll.

Plants (Basel, Switzerland)·2024

Same author

An Efficient Method for Monitoring Birds Based on Object Detection and Multi-Object Tracking Networks.

Animals : an open access journal from MDPI·2023

Same author

Combined spectral and speech features for pig speech recognition.

PloS one·2022

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 10, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

MAF-MixNet: Few-Shot Tea Disease Detection Based on Mixed Attention and Multi-Path Feature Fusion.

Wenjing Zhang¹, Ke Tan¹, Han Wang¹

¹College of Information Engineering, Sichuan Agricultural University, Ya'an 625014, China.

Plants (Basel, Switzerland)

|April 26, 2025

Summary

This summary is machine-generated.

This study introduces MAF-MixNet, a deep learning model for tea plant disease detection using minimal data. It significantly improves accuracy in identifying diseases like anthracnose and brown blight, enabling efficient agricultural monitoring.

Keywords:

attention mechanism feature fusion few-shot object detection tea disease detection

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

Related Experiment Videos

Last Updated: May 10, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

Area of Science:

Agricultural Science
Computer Vision
Deep Learning

Background:

Tea disease detection in fields is challenging due to limited labeled data, hindering deep learning models.
Existing methods struggle with feature extraction from scarce samples.

Purpose of the Study:

To develop a novel few-shot end-to-end detection network (MAF-MixNet) for robust tea disease detection with minimal annotations.
To overcome feature extraction limitations in low-data scenarios.

Main Methods:

Proposed MAF-MixNet featuring a mixed attention branch (MA-Branch) for contextual features and a multi-path feature fusion module (MAFM) for enhanced local/global feature combination.
Employed a two-stage training: pretraining on public datasets and fine-tuning on balanced subsets including new tea disease classes.
Conducted comparative experiments against six models using four evaluation metrics.

Main Results:

At 5-shot, MAF-MixNet achieved 62.0% precision, 60.1% nAP50, and 65.9% F1 score, outperforming other models.
In the 10-shot scenario, nAP50 reached 73.8%.
The model demonstrated computational efficiency with the second fastest inference speed (11.63 FPS).

Conclusions:

MAF-MixNet effectively addresses the challenge of limited labeled data for tea disease detection.
The model shows significant potential for cost-effective, intelligent disease monitoring in precision agriculture.
The proposed architecture enhances feature extraction and fusion for improved performance in few-shot learning scenarios.