文献类型： 外文期刊
作者： Zheng, Jiye 1 ; Li, Kaiyu 1 ; Wu, Wenbin 3 ; Ruan, Huaijun 1 ;
作者机构： 1.Shandong Acad Agr Sci, Inst Agr Informat & Econ, Jinan 250100, Peoples R China
2.Shandong Univ Sci & Technol, Coll Comp Sci & Engn, Qingdao 266590, Peoples R China
3.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, Beijing 100081, Peoples R China
关键词： Disease identification; Image processing; Deep learning; Lightweight model
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.3； 五年影响因子：8.3 ）
ISSN： 0168-1699
年卷期： 2023 年 212 卷
页码：
收录情况： SCI
摘要： Apple disease is one of the major factors affecting apple production, and the visual diagnosis of apple leaves is an efficient disease identification solution. In this paper, we propose an efficient lightweight model based on structural reparameterization for apple leaf disease identification, called RepDI for short. To achieve faster inference on the CPU devices, we introduce depth-wise separable convolution and structural reparameterization technology in RepDI, which has different structures during training and inference. In addition, to better capture diseased leaves and disease regions in complex contexts, we propose the parallel dilated attention mechanism module and embed it into RepDI. Experiments show that RepDI can achieve state-of-the-art performance in disease identification task, compared to most lightweight models. Meanwhile, RepDI achieves the fastest inference speed on our desktop CPU, which is an important factor in practical applications. Furthermore, we collect and annotate a novel dataset for apple leaf diseases from real scenarios, called Real-ALD, which is more challenging than previous datasets. And RepDI achieves a top-1 accuracy of 98.92 in the Real-ALD dataset under a limited training configuration. Our code is released to contribute to the plant protection community and we will further explore the potential of RepDI for down-stream detection, segmentation tasks.
- 相关文献
作者其他论文 更多>>
-
Causal relationship analysis of high-dimensional time series based on quantile factor model
作者：Liu, Hui;Liang, Huiling;Liu, Liwei;Liu, Hui;Liang, Huiling;Liu, Liwei;Zhao, Jia;Ruan, Huaijun
关键词：High-dimensional time series; Quantile factor model; Conditional granger causality analysis; Data mining
-
An edge-guided method to fruit segmentation in complex environments
作者：Sheng, Xing;Kang, Chunmeng;Lyu, Chen;Zheng, Jiye
关键词：Instance segmentation; Edge -guided fruit segmentation; GLM; MSLB; BAM
-
ALAE: self-attention reconstruction network for multivariate time series anomaly identification
作者：Jiang, Kai;Liu, Hui;Lin, Yuxiu;Jiang, Kai;Liu, Hui;Lin, Yuxiu;Ruan, Huaijun;Zhao, Jia
关键词：Multivariate time series; Anomaly detection; Data reconstruction; Self-attention mechanism
-
Disease diagnostic method based on cascade backbone network for apple leaf disease classification
作者：Sheng, Xing;Wang, Fengyun;Ruan, Huaijun;Fan, Yangyang;Zheng, Jiye;Sheng, Xing;Zhang, Yangyang;Lyu, Chen
关键词：cascade decoder; cascade backbone network; Transformer; applet; disease classification
-
Estimation model of soluble solids content in bagged and non-bagged apple fruits based on spectral data
作者：Wang, Fengyun;Zheng, Jiye;Qi, Kangkang;Fan, Yangyang;Ruan, Huaijun;Zhao, Yimin;Yuan, Xulin
关键词：Bagged apple fruit; Non-bagged apple fruit; Soluble solids content; Spectral data
-
Classification Method Research of Fresh Agaricus Bisporus Based on Image Processing
作者：Wang, Fengyun;Zheng, Jiye;Wang, Lei;Feng, Wenjie;Niu, Luyan
关键词：Agaricus bisporus; Image processing; Maximum entropy threshold segmentation; Watershed algorithm
-
Study on Photosynthetic Rate of Wheat under Powdery Mildew Stress using Hyperspectral Image
作者：Zhang, Xiaoyan;Niu, Luyan;Sun, Jiabo;Wang, Lili;Zheng, Jiye;Liu, Yanzhong;Zhang, Junli
关键词：Estimation model; Hyperspectral imaging; Photosynthetic rate; Powdery mildew; Wheat
