Detection and Maturity Classification of Dense Small Lychees Using an Improved Kolmogorov–Arnold Network–Transformer
Open Access
Abstract
Lychee detection and maturity classification are crucial for yield estimation and harvesting. In densely packed lychee clusters with limited training samples, accurately determining ripeness is challenging. This paper proposes a new transformer model incorporating a Kolmogorov–Arnold Network (KAN), termed GhostResNet (GRN)–KAN–Transformer, for lychee detection and ripeness classification in dense on-tree fruit clusters. First, within the backbone, we introduce a stackable multi-layer GhostResNet module to reduce redundancy in feature extraction and improve efficiency. Next, during feature fusion, we add a large-scale layer to enhance sensitivity to small objects and to increase polling of the small-scale feature map during querying. We further propose a multi-layer cross-fusion attention (MCFA) module to achieve deeper hierarchical feature integration. Finally, in the decoding stage, we employ an improved KAN for the classification and localization heads to strengthen nonlinear mapping, enabling a better fitting to the complex distributions of categories and positions. Experiments on a public dataset demonstrate the effectiveness of GRN-KANformer. Compared with the baseline, GFLOPs and parameters of the model are reduced by 8.84% and 11.24%, respectively, while mean Average Precision (mAP) metrics mAP50 and mAP50–95 reach 94.7% and 58.4%, respectively. Thus, it lowers computational complexity while maintaining high accuracy. Comparative results against popular deep learning models, including YOLOv8n, YOLOv12n, CenterNet, and EfficientNet, further validate the superior performance of GRN-KANformer.Keywords
Funding Information
- The Shenzhen Talent Startup Funds (827-000954)
- Shenzhen University (86902/00248)
This publication has 61 references indexed in Scilit:
- Multi-scale cross-modal feature fusion and cost-sensitive loss function for differential detection of occluded bagging pears in practical orchardsArtificial Intelligence in Agriculture, 2025
- Robust real-time blueberry counting in greenhouses using small-object detection and mamba-driven multi-step trajectory completionSmart Agricultural Technology, 2025
- Incremental learning with domain adaption for tomato plant phenotypingSmart Agricultural Technology, 2025
- MTAD-Kanformer: multivariate time-series anomaly detection via kan and transformerApplied Intelligence, 2025
- A survey of automated data augmentation algorithms for deep learning-based image classification tasksKnowledge and Information Systems, 2023
- An effective litchi detection method based on edge devices in a complex sceneBiosystems Engineering, 2022
- Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D imagesPrecision Agriculture, 2020
- Visual positioning technology of picking robots for dynamic litchi clusters with disturbanceComputers and Electronics in Agriculture, 2018
- The recognition of litchi clusters and the calculation of picking point in a nocturnal natural environmentBiosystems Engineering, 2018
- AE—Automation and Emerging TechnologiesBiosystems Engineering, 2002