Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Light Acquisition02:16

Light Acquisition

9.3K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.3K

You might also read

Related Articles

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

Sort by
Same author

Non-structural carbohydrates in maize with different nitrogen tolerance are affected by nitrogen addition.

PloS one·2019
Same author

Knockdown of long noncoding RNA XIST mitigates the apoptosis and inflammatory injury of microglia cells after spinal cord injury through miR-27a/Smurf1 axis.

Neuroscience letters·2019
Same author

One-Step Hydrothermal Synthesis of P25 @ Few Layered MoS<sub>2</sub> Nanosheets toward Enhanced Bi-catalytic Activities: Photocatalysis and Electrocatalysis.

Nanomaterials (Basel, Switzerland)·2019
Same author

Electrospun thymosin Beta-4 loaded PLGA/PLA nanofiber/ microfiber hybrid yarns for tendon tissue engineering application.

Materials science & engineering. C, Materials for biological applications·2019
Same author

Risk factors for implant failure in reverse oblique and transverse intertrochanteric fractures treated with proximal femoral nail antirotation (PFNA).

Journal of orthopaedic surgery and research·2019
Same author

Xestospongin C, a Reversible IP3 Receptor Antagonist, Alleviates the Cognitive and Pathological Impairments in APP/PS1 Mice of Alzheimer's Disease.

Journal of Alzheimer's disease : JAD·2019
Same journal

Machine learning to predict genotypes and genotype-environment interaction associated with complex traits for genomic selection.

Plant phenomics (Washington, D.C.)·2026
Same journal

FQGR-net: Morphology-based litchi flower quantification and gender recognition.

Plant phenomics (Washington, D.C.)·2026
Same journal

Thermal image segmentation in weedy fields via synthetic RGB-trained models and GAN-based cross-modality alignment.

Plant phenomics (Washington, D.C.)·2026
Same journal

Unlocking almond breeding for nutritional composition with hyperspectral imaging.

Plant phenomics (Washington, D.C.)·2026
Same journal

From plots to commercial fields: scalable, transferable cotton morphology and productivity estimation using functional growth proxies from UAV and PlanetScope time series.

Plant phenomics (Washington, D.C.)·2026
Same journal

Deep learning-driven automatic counting of petal number in cut chrysanthemum inflorescence.

Plant phenomics (Washington, D.C.)·2026
See all related articles

Related Experiment Video

Updated: Jan 8, 2026

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM
08:43

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM

Published on: June 24, 2017

7.8K

Multi-granularity alignment for crop diseases detection.

Guinan Guo1, Fang Zhou1, Qingyang Wu2

  • 1School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510700, China.

Plant Phenomics (Washington, D.C.)
|December 19, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces Multi-Granularity Alignment (MGA), a novel framework for cross-domain crop disease detection. MGA significantly improves model performance on new datasets by aligning features and reducing disparities, aiding the "zero hunger" goal.

Keywords:
Crop diseasesCross domainDomain adaptationObject detection

More Related Videos

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.5K

Related Experiment Videos

Last Updated: Jan 8, 2026

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM
08:43

Highly Multiplexed, Super-resolution Imaging of T Cells Using madSTORM

Published on: June 24, 2017

7.8K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.5K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Crop diseases pose a significant threat to global food security and achieving the sustainable development goal of "zero hunger."
  • Variations in data collection conditions create domain shift issues, leading to poor performance of crop disease detection models on new datasets.
  • Existing object detection models struggle with cross-domain generalization, hindering their real-world applicability in diverse agricultural settings.

Purpose of the Study:

  • To propose a novel domain adaptation framework, Multi-Granularity Alignment (MGA), to address the challenges of cross-domain crop disease object detection.
  • To enhance the generalizability and compatibility of object detection models for detecting crop diseases across different domains.
  • To align feature representations between source and target domains, reducing disparities and improving detection accuracy.

Main Methods:

  • Developed the Multi-Granularity Alignment (MGA) framework, integrating multi-granularity alignment and omni-scale gated fusion domain adaptation components.
  • Implemented scale-aware convolutional aggregation on feature maps within an enhanced object detector.
  • Utilized three levels of discriminators (category, instance, and pixel) for domain alignment from a granularity-dependent perspective.

Main Results:

  • MGA achieved state-of-the-art mean Average Precision (mAP) scores across various cross-domain datasets, including 47.9% (PVi → CDi), 48.3% (PDc → PVi), and 49.2% (Data with style transfer → CDi).
  • The framework demonstrated superior performance compared to existing object detection technologies.
  • When integrated with Faster R-CNN, MGA achieved an mAP of 44.7% on the CDi → Data w/style transfer dataset, showcasing robust generalization.

Conclusions:

  • The Multi-Granularity Alignment (MGA) framework effectively addresses cross-domain challenges in crop disease detection.
  • MGA significantly improves model performance and generalization capabilities across diverse datasets and environments.
  • This approach holds promise for advancing precision agriculture and contributing to global food security initiatives.