Original Articles Open access

MSIFD-Net: tea stem recognition network based on multi-scale interaction combined feature decoupling

Authors

Published
11 November 2026
Issue
Early Access
Section
Original Articles
DOI
10.4081/jae.2026.2317

Abstract

Accurate tea bud detection is essential for intelligent tea-picking robots. After multiple harvests, tea stems appear more frequently, and many tea bud detection models misclassify stems as buds due to subtle differences in shape, texture, and color. Such errors reduce detection accuracy and may damage the end effector when rigid stems are mistakenly selected. In order to reduce the false identification of tea stems as buds, this study proposes a tea stem recognition network based on multi-scale interaction combined with feature decoupling (MSIFD-Net), which operates at the output of a tea bud detection model. The network exploits shallow and deep features to enhance fine-grained discrimination. An Adaptive Channel–Spatial Attention module suppresses irrelevant responses in multi-scale features and emphasizes key spatial regions and channels. A multi-scale interaction structure extracts complementary information from global features across different scales. In addition, a feature decoupling module separates feature components into independent subspaces to reduce redundancy. On the ZC108 dataset, the integration of MSIFD-Net into YOLOv11 achieved a peak AP of 91.28%, improving by 10.23 percentage points compared with YOLOv11 without MSIFD-Net. Furthermore, the FDR decreased markedly from 22.22% to 1.1%, representing a reduction of 21.12 percentage points. These results demonstrated that the proposed method effectively reduced false detections caused by residual tea stems and decreased the risk of unnecessary picking operations and potential damage to the tea-picking robot end effector.

Keywords

Supporting Agencies

National Key Research and Development Program of China, National Natural Science Foundation of China, China Agriculture Research System (CARS-19)

Data Availability Statement

The data used to support the findings of this study are available from the corresponding author upon reasonable request.

References

  1. Bousmalis K, Trigeorgis G, Silberman N, Krishnan D, Erhan D, 2016. Domain separation networks. arXiv:1608.06019v1
  2. Chen YT, Chen SF, 2020. Localizing plucking points of tea leaves using deep convolutional neural networks. Comput Electron Agr 171:105298. DOI: https://doi.org/10.1016/j.compag.2020.105298
  3. Ge Z, Liu S, Wang F, Li Z, Sun J, 2021. YOLOX: Exceeding YOLO series in 2021. arXiv:2107.08430
  4. Gui Z, Chen J, Li Y, Chen Z, Wu C, Dong C, 2023. A lightweight tea bud detection model based on YOLOv5. Comput Electron Agr 205:107636. DOI: https://doi.org/10.1016/j.compag.2023.107636
  5. Guo S, Yoon SC, Li L, Wang W, Zhuang H, Wei C, et al., 2023. Recognition and positioning of fresh tea buds using YOLOv4-lighted and ICBAM model and RGB-D sensing. Agriculture 13:518. DOI: https://doi.org/10.3390/agriculture13030518
  6. He K, Zhang X, Ren S, Sun J, 2016. Deep residual learning for image recognition. Proc. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas; pp. 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90
  7. Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, et al., 2019. Searching for MobileNetV3. Proc. IEEE/CVF International Conference on Computer Vision, Seoul; pp. 1314-1324. DOI: https://doi.org/10.1109/ICCV.2019.00140
  8. Hu J, Shen L, Sun G, 2018. Squeeze-and-excitation networks. Proc. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City; pp. 7132-7141. DOI: https://doi.org/10.1109/CVPR.2018.00745
  9. Huang H, Chen Z, Zou Y, Lu M, Chen C, Song Y, et al., 2024. Channel prior convolutional attention for medical image segmentation. Comput Biol Med 178:108784. DOI: https://doi.org/10.1016/j.compbiomed.2024.108784
  10. Kumar PVS, Basheer S, Ravi R, Thakur MS, 2011. Comparative assessment of tea quality by various analytical and sensory methods with emphasis on tea. J Food Sci Technol 48:440-446. DOI: https://doi.org/10.1007/s13197-010-0178-y
  11. Liu P, Qiu X, Huang X, 2017. Adversarial multi-task learning for text classification. arXiv:1704.05742 DOI: https://doi.org/10.18653/v1/P17-1001
  12. Liu Y, Shao Z, Hoffmann N, 2021. Global attention mechanism: retain information to enhance channel-spatial interactions. arXiv:2112.05561.
  13. Ma N, Zhang X, Zheng HT, Sun J, 2018. ShuffleNet V2: practical guidelines for efficient CNN architecture design. Proc. European Conference on Computer Vision, Munich; pp. 116-131. DOI: https://doi.org/10.1007/978-3-030-01264-9_8
  14. Ruder S, Plank B, 2018. Strong baselines for neural semi-supervised learning under domain shift. arXiv:1804.09530 DOI: https://doi.org/10.18653/v1/P18-1096
  15. Salzmann M, Ek CH, Urtasun R, Darrell T, 2010. Factorized orthogonal latent spaces. Proc. 13th Int. Conf. on Artificial Intelligence and Statistics, Chia; pp. 701-708.
  16. Song Y, Morency LP, Davis R, 2012. Multi-view latent variable discriminative models for action recognition. Proc. IEEE Conference on Computer Vision and Pattern Recognition, Providence; pp. 2120-2127. DOI: https://doi.org/10.1109/CVPR.2012.6247918
  17. Wang S, Wu D, Zheng X, 2023a. TBC-YOLOv7: a refined YOLOv7-based algorithm for tea bud grading detection. Front Plant Sci 14:1223410. DOI: https://doi.org/10.3389/fpls.2023.1223410
  18. Wang T, Zhang K, Zhang W, Wang R, Wan S, Rao Y, et al., 2023b. Tea picking point detection and location based on Mask-RCNN. Inf Process Agric 10:267-275. DOI: https://doi.org/10.1016/j.inpa.2021.12.004
  19. Woo S, Park J, Lee JY, Kweon IS, 2018. CBAM: convolutional block attention module. Proc. European Conference on Computer Vision, Munich; pp. 3-19. DOI: https://doi.org/10.1007/978-3-030-01234-2_1
  20. Xie S, Sun H, 2023. Tea-YOLOv8s: a tea bud detection model based on deep learning and computer vision. Sensors (Basel) 23:6576. DOI: https://doi.org/10.3390/s23146576
  21. Yang M, Yuan W, Xu G, 2024. YOLOX target detection model can identify and classify several types of tea buds with similar characteristics. Sci Rep 14:2855. DOI: https://doi.org/10.1038/s41598-024-53498-y
  22. Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, Liu Y, Chen J, 2024. DETRs beat YOLOs on real-time object detection. Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle; pp. 16965–16974. DOI: https://doi.org/10.1109/CVPR52733.2024.01605
  23. Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A, 2016. Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas; pp. 2921-2929. DOI: https://doi.org/10.1109/CVPR.2016.319

Metrics

Citations and online attention from Dimensions, Altmetric and PlumX.

PlumX Metrics

License

Copyright (c) 2026 the Author(s)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.