Soy-RepViT: a lightweight deep learning framework for fine-grained recognition of soybean growth habits
- 1College of Intelligence Science and Engineering, Northeast Agricultural University, Harbin , ,
- 2State Key Laboratory of Smart Farm Technologies and Systems , ,
Abstract
Soybean growth habit is generally classified into determinate, indeterminate, and semi-determinate types, and its accurate recognition is important for breeding selection, high-density cultivation, and agronomic management. However, the semi-determinate type is intermediate between determinate and indeterminate types and shows continuous transitional characteristics with the indeterminate type in stem elongation, upper internode length, and pod distribution, making fine-grained discrimination between these two types difficult. Practical deployment also requires lightweight, efficient models. This study developed a lightweight fine-grained recognition framework for soybean growth habit from standardized plant images. The framework used RepViT-M1 as an efficient feature extraction backbone and integrated a multi-scale efficient channel attention module (MS-ECA) to enhance discriminative channel features, a Fine-grained Disambiguation Adapter (FDA) to recalibrate non-determinate features using class prototypes and reduce indeterminate/semi-determinate confusion, and a hierarchical classification head to incorporate the agronomic hierarchy between determinate and non-determinate types. The dataset comprised 944 original soybean plant images and was expanded to 4,709 images through offline augmentation. The model was evaluated using five-fold cross-validation and an independent test set. The proposed model achieved 97.45% accuracy on the independent test set, improving the RepViT-M1 baseline by approximately 3 percentage points. Accuracy for the indeterminate type increased from 91.30% to 97.83%, indicating that the model effectively reduced confusion between indeterminate and semi-determinate types. The model had 4.94 M parameters, required 0.82 GFLOPs, and reached 108.75 FPS, demonstrating a favorable balance between accuracy and efficiency. The proposed framework improves fine-grained soybean growth habit recognition at low computational cost and demonstrates potential for standardized, high-throughput phenotypic identification through on-device Android inference.
Related
- Lightweight frequency-aware hybrid vision transformer for fine-grained plant disease recognition
- HECA-MobileNet: an explainable lightweight attention-based deep learning framework for custard apple disease detection
- Fine-grained sugarcane varietal classification using high-resolution PRSS-1 satellite imagery: a field-validated dataset and a spatial context-aware deep learning framework
- MambaSeed: A lightweight Mamba-based hybrid vision network for tomato leaf disease recognition
- Probing EEG Foundation Model Attention Maps for Lightweight Interpretable Emotion Recognition
BibTeX
@article{liu2026soyrepvit,
title = {{Soy-RepViT: a lightweight deep learning framework for fine-grained recognition of soybean growth habits}},
author = {Dongbo Liu and Daohan Cui and Hang Liu and Tianyuan Song and Zhanguo Zhang and Qingshan Chen and Fanchuang Li and Rongsheng Zhu},
journal = {Frontiers in plant science},
year = {2026},
month = sep,
doi = {10.3389/fpls.2026.1954156},
url = {https://europepmc.org/article/PMC/PMC13661940},
note = {CC BY},
}
RIS
TY - JOUR
TI - Soy-RepViT: a lightweight deep learning framework for fine-grained recognition of soybean growth habits
AU - Dongbo Liu
AU - Daohan Cui
AU - Hang Liu
AU - Tianyuan Song
AU - Zhanguo Zhang
AU - Qingshan Chen
AU - Fanchuang Li
AU - Rongsheng Zhu
PY - 2026
DA - 2026/09/30
JO - Frontiers in plant science
DO - 10.3389/fpls.2026.1954156
UR - https://europepmc.org/article/PMC/PMC13661940
AB - Soybean growth habit is generally classified into determinate, indeterminate, and semi-determinate types, and its accurate recognition is important for breeding selection, high-density cultivation, and agronomic management. However, the semi-determinate type is intermediate between determinate and indeterminate types and shows continuous transitional characteristics with the indeterminate type in stem elongation, upper internode length, and pod distribution, making fine-grained discrimination between these two types difficult. Practical deployment also requires lightweight, efficient models. This study developed a lightweight fine-grained recognition framework for soybean growth habit from standardized plant images. The framework used RepViT-M1 as an efficient feature extraction backbone and integrated a multi-scale efficient channel attention module (MS-ECA) to enhance discriminative channel features, a Fine-grained Disambiguation Adapter (FDA) to recalibrate non-determinate features using class prototypes and reduce indeterminate/semi-determinate confusion, and a hierarchical classification head to incorporate the agronomic hierarchy between determinate and non-determinate types. The dataset comprised 944 original soybean plant images and was expanded to 4,709 images through offline augmentation. The model was evaluated using five-fold cross-validation and an independent test set. The proposed model achieved 97.45% accuracy on the independent test set, improving the RepViT-M1 baseline by approximately 3 percentage points. Accuracy for the indeterminate type increased from 91.30% to 97.83%, indicating that the model effectively reduced confusion between indeterminate and semi-determinate types. The model had 4.94 M parameters, required 0.82 GFLOPs, and reached 108.75 FPS, demonstrating a favorable balance between accuracy and efficiency. The proposed framework improves fine-grained soybean growth habit recognition at low computational cost and demonstrates potential for standardized, high-throughput phenotypic identification through on-device Android inference.
SN - 1664-462X
ER -