An improved YOLOv11 algorithm for rice diseases

Tao Wang, Changming Zhu
Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, PMLR 278:359-368, 2025.

Abstract

The timely identification of rice diseases is of vital importance to national food security. This paper proposes an improved model based on YOLOv11, and uses three key innovations to enhance the detection performance of the model. Firstly, DynamicConv enables the network to increase the number of parameters while maintaining a low number of floating-point operations (FLOPs), allowing these networks to benefit from large-scale visual pre-training. Secondly, the iterative attention feature fusion (iAFF) improves the detection accuracy by enhancing the feature fusion process. In addition, the Synergistic Cross-Scale Attention module (SCSA) is designed to effectively combine the advantages of channel and spatial attention, making full use of multi-semantic information, thus improving the performance of visual tasks. The experimental results show that the innovated model can effectively improve the detection efficiency of rice diseases, providing a reliable solution for agricultural security.

Cite this Paper

BibTeX
@InProceedings{pmlr-v278-wang25e, title = {An improved YOLOv11 algorithm for rice diseases}, author = {Wang, Tao and Zhu, Changming}, booktitle = {Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing}, pages = {359--368}, year = {2025}, editor = {Zeng, Nianyin and Pachori, Ram Bilas and Wang, Dongshu}, volume = {278}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v278/main/assets/wang25e/wang25e.pdf}, url = {https://proceedings.mlr.press/v278/wang25e.html}, abstract = {The timely identification of rice diseases is of vital importance to national food security. This paper proposes an improved model based on YOLOv11, and uses three key innovations to enhance the detection performance of the model. Firstly, DynamicConv enables the network to increase the number of parameters while maintaining a low number of floating-point operations (FLOPs), allowing these networks to benefit from large-scale visual pre-training. Secondly, the iterative attention feature fusion (iAFF) improves the detection accuracy by enhancing the feature fusion process. In addition, the Synergistic Cross-Scale Attention module (SCSA) is designed to effectively combine the advantages of channel and spatial attention, making full use of multi-semantic information, thus improving the performance of visual tasks. The experimental results show that the innovated model can effectively improve the detection efficiency of rice diseases, providing a reliable solution for agricultural security.} }
Endnote
%0 Conference Paper %T An improved YOLOv11 algorithm for rice diseases %A Tao Wang %A Changming Zhu %B Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2025 %E Nianyin Zeng %E Ram Bilas Pachori %E Dongshu Wang %F pmlr-v278-wang25e %I PMLR %P 359--368 %U https://proceedings.mlr.press/v278/wang25e.html %V 278 %X The timely identification of rice diseases is of vital importance to national food security. This paper proposes an improved model based on YOLOv11, and uses three key innovations to enhance the detection performance of the model. Firstly, DynamicConv enables the network to increase the number of parameters while maintaining a low number of floating-point operations (FLOPs), allowing these networks to benefit from large-scale visual pre-training. Secondly, the iterative attention feature fusion (iAFF) improves the detection accuracy by enhancing the feature fusion process. In addition, the Synergistic Cross-Scale Attention module (SCSA) is designed to effectively combine the advantages of channel and spatial attention, making full use of multi-semantic information, thus improving the performance of visual tasks. The experimental results show that the innovated model can effectively improve the detection efficiency of rice diseases, providing a reliable solution for agricultural security.
APA
Wang, T. & Zhu, C.. (2025). An improved YOLOv11 algorithm for rice diseases. Proceedings of 2025 2nd International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 278:359-368 Available from https://proceedings.mlr.press/v278/wang25e.html.

Related Material