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 Experiment Video

Updated: Jul 1, 2026

Computer Vision-Based Biomass Estimation for Invasive Plants
08:47

Computer Vision-Based Biomass Estimation for Invasive Plants

Published on: February 9, 2024

Crop-weed classification using deep learning: a comparative study of CNNs, vision transformers, and interpretable

Rishi Chaudhary1,2, Akshay Agarwal3, Ved Prakash Chaudhary4

  • 1Shiv Nadar University IoE, Gautam Buddha Nagar, Dadri, 201314, Uttar Pradesh, India. rc680@snu.edu.in.

Scientific Reports
|June 29, 2026
PubMed
Summary

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

Development and performance evaluation of variable width raised bed former with optimal parameters predicted by RBF neural network-PSO technique.

Scientific reports·2026
Same author

Advancements in MRI Conditionality of Spinal Cord Stimulation Systems: A Narrative Review of Recent SCS Systems and Their Associated Risks in MRI Operations.

Pain physician·2025
Same author

Bayesian-optimized recursive machine learning for predicting human-induced changes in suspended sediment transport.

Environmental monitoring and assessment·2025
Same author

De novo virulence feature discovery and risk assessment in Klebsiella pneumoniae based on microbial genome vectorization.

Communications biology·2025
Same author

Development and evaluation of statistical and artificial intelligence approaches with microbial shotgun metagenomics data as an untargeted screening tool for use in food production.

mSystems·2024
Same author

Shot noise-mitigated secondary electron imaging with ion count-aided microscopy.

Proceedings of the National Academy of Sciences of the United States of America·2024
Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026
Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026
Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026
Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026
Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026
Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026
See all related articles
This summary is machine-generated.

High-quality data is crucial for accurate crop-weed classification in precision agriculture. Models like CLIP and PIPNet show promise for robust performance, even with varying image conditions and domain shifts.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Machine Learning

Background:

  • Precision agriculture relies on accurate crop-weed classification for efficient resource management.
  • Challenges include label noise, varying illumination, domain shifts, and diverse imaging conditions.

Purpose of the Study:

  • Evaluate deep learning models for crop-weed classification.
  • Assess the impact of data quality and domain shifts on model performance.
  • Identify robust models for practical agricultural applications.

Main Methods:

  • Compared five deep learning models: ResNet50, ResNet101, Vision Transformer (ViT), CLIP, and PIPNet.
  • Utilized two datasets with differing acquisition conditions and annotation quality.
  • Conducted cross-dataset evaluations to assess generalization capabilities.
Keywords:
CLIPCrop-weed classificationDeep learningDomain adaptationInterpretable AIPrecision agricultureVision transformers

Related Experiment Videos

Last Updated: Jul 1, 2026

Computer Vision-Based Biomass Estimation for Invasive Plants
08:47

Computer Vision-Based Biomass Estimation for Invasive Plants

Published on: February 9, 2024

Main Results:

  • Model performance was strongly influenced by data quality; clean data yielded 25-30% improvement.
  • Cross-dataset evaluation showed accuracy drops up to 50% due to domain shift.
  • CLIP and PIPNet demonstrated robustness to image corruptions and domain shifts.
  • PIPNet achieved the highest accuracy on clean data and provided interpretable predictions.

Conclusions:

  • High-quality annotations are essential for reliable crop-weed classification.
  • Models with semantic understanding and interpretability (CLIP, PIPNet) show greater potential.
  • Future research should focus on developing adaptive models for diverse field conditions.