Multi-crop disease classification using a Dilateformer-MobileNetV2 dual-branch fusion network
Abstract
Multi-crop disease classification requires discrimination among visually similar symptoms. This study evaluates late feature fusion of Dilateformer and MobileNetV2 for 45-class image classification. The two pooled representations are concatenated before classification. The original experiment achieved 97.21% Top-1 accuracy and 96.63% macro F1 on a 59,905-image benchmark. During revision, PlantDoc-derived samples were added to the existing collection to broaden image diversity. On this expanded 68,682-sample dataset, the selected fusion checkpoint achieved 95.45% accuracy and 93.63% macro F1 on 6,550 test samples, compared with 95.48% accuracy for MobileNetV2. These results belong to distinct data and implementation versions. Dataset provenance, parameter accounting and branch-specific gradient-weighted class activation mapping (Grad-CAM) support interpretation of the revision-stage results. The findings demonstrate useful multi-crop classification performance, while showing that simple feature concatenation does not guarantee improvement over a single branch. Independent field generalization remains to be established.
Related
- Citrus leaf pathology multi-class image dataset and a hybrid multi-branch attention fusion network for lemon leaf disease classification
- IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT
- Application of Bayesian-Derived Gene Interaction Network and Subnetwork for Classification of Idiopathic Parkinson Disease with Biomarkers
- DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
- A Complementary Dual-Branch Receptive Field Network for Cross-Channel-Density Motor Imagery EEG Decoding.
BibTeX
@article{gu2026multicrop,
title = {{Multi-crop disease classification using a Dilateformer-MobileNetV2 dual-branch fusion network}},
author = {Rongrong Gu and Zhigang Huang and Yang Zhang and Shengyi Zhao and Yunming Zhao and Jiasheng Jiang and Xi Kan and Qingan Da and Nan Fu and Jizhang Wang},
journal = {Frontiers in Plant Science},
year = {2026},
month = nov,
doi = {10.3389/fpls.2026.1961479},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1961479},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multi-crop disease classification using a Dilateformer-MobileNetV2 dual-branch fusion network
AU - Rongrong Gu
AU - Zhigang Huang
AU - Yang Zhang
AU - Shengyi Zhao
AU - Yunming Zhao
AU - Jiasheng Jiang
AU - Xi Kan
AU - Qingan Da
AU - Nan Fu
AU - Jizhang Wang
PY - 2026
DA - 2026/11/09
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1961479
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1961479
AB - Multi-crop disease classification requires discrimination among visually similar symptoms. This study evaluates late feature fusion of Dilateformer and MobileNetV2 for 45-class image classification. The two pooled representations are concatenated before classification. The original experiment achieved 97.21% Top-1 accuracy and 96.63% macro F1 on a 59,905-image benchmark. During revision, PlantDoc-derived samples were added to the existing collection to broaden image diversity. On this expanded 68,682-sample dataset, the selected fusion checkpoint achieved 95.45% accuracy and 93.63% macro F1 on 6,550 test samples, compared with 95.48% accuracy for MobileNetV2. These results belong to distinct data and implementation versions. Dataset provenance, parameter accounting and branch-specific gradient-weighted class activation mapping (Grad-CAM) support interpretation of the revision-stage results. The findings demonstrate useful multi-crop classification performance, while showing that simple feature concatenation does not guarantee improvement over a single branch. Independent field generalization remains to be established.
SN - 1664-462X
ER -