Soybean Leaf Disease Classification

This repository contains the source code, experimental configurations, algorithmic pseudocode, evaluation scripts, and reference results required to support the reproducibility of the research paper entitled "Hybrid Local–Global Feature Learning for Soyabean Leaf Disease Classification Using EfficientNetV2 and Swin Transformer". The proposed framework integrates EfficientNetV2 and Swin Transformer to learn complementary local and global features for soybean leaf disease classification. The repository includes Python implementation files, model architecture, dataset handling and preprocessing modules, training and evaluation scripts, cross-dataset validation procedures, ablation study implementations, statistical analysis scripts, and experimental configuration files. It also provides manuscript-reported reference results, including classification performance, baseline comparisons, cross-dataset generalization results, attention-fusion ablation studies, and computational efficiency measurements. The purpose of this repository is to support transparency, facilitate independent evaluation, and improve the reproducibility of the experimental methodology and findings reported in the manuscript. Associated manuscript: Hybrid Local–Global Feature Learning for Soyabean Leaf Disease Classification Using EfficientNetV2 and Swin Transformer.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24339850
Primary Topic
Smart Agriculture and AI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Soybean Leaf Disease Classification

Parul Dubey, Amol Chokhat
5 links
Zenodo (CERN European Organization for Nuclear Research)
Smart Agriculture and AI
article

Soybean Leaf Disease Classification

Parul Dubey, Amol Chokhat
article en

Abstract

This repository contains the source code, experimental configurations, algorithmic pseudocode, evaluation scripts, and reference results required to support the reproducibility of the research paper entitled "Hybrid Local–Global Feature Learning for Soyabean Leaf Disease Classification Using EfficientNetV2 and Swin Transformer". The proposed framework integrates EfficientNetV2 and Swin Transformer to learn complementary local and global features for soybean leaf disease classification. The repository includes Python implementation files, model architecture, dataset handling and preprocessing modules, training and evaluation scripts, cross-dataset validation procedures, ablation study implementations, statistical analysis scripts, and experimental configuration files. It also provides manuscript-reported reference results, including classification performance, baseline comparisons, cross-dataset generalization results, attention-fusion ablation studies, and computational efficiency measurements. The purpose of this repository is to support transparency, facilitate independent evaluation, and improve the reproducibility of the experimental methodology and findings reported in the manuscript. Associated manuscript: Hybrid Local–Global Feature Learning for Soyabean Leaf Disease Classification Using EfficientNetV2 and Swin Transformer.

Zenodo (CERN European Organization for Nuclear Research)
Zero hunger
Smart Agriculture and AI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon