Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification
Combining disease categories and crop species leads to complex intra-class and inter-class differences. Significant intra-class difference and subtle inter-class difference pose a great challenge to high-precision crop disease classification tasks. To this end, we propose a multi-granularity feature...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/12/9/1499 |
| _version_ | 1797492280177721344 |
|---|---|
| author | Xin Zuo Jiao Chu Jifeng Shen Jun Sun |
| author_facet | Xin Zuo Jiao Chu Jifeng Shen Jun Sun |
| author_sort | Xin Zuo |
| collection | DOAJ |
| description | Combining disease categories and crop species leads to complex intra-class and inter-class differences. Significant intra-class difference and subtle inter-class difference pose a great challenge to high-precision crop disease classification tasks. To this end, we propose a multi-granularity feature aggregation method for accurately identifying disease types and crop species as well as better understanding the disease-affected regions implicitly. Specifically, in order to capture fine-grained discriminating clues to disease categories, we first explored the pixel-level spatial self-attention to model the pair-wise semantic relations. Second, we utilized the block-level channel self-attention to enhance the feature-discriminative ability of different crop species. Finally, we used a spatial reasoning module to model the spatial geometric relationship of the image patches sequentially, such that the feature-discriminative ability of characterizing both diseases and species is further improved. The proposed model was verified on the PDR2018 dataset, the FGVC8 dataset, and the non-lab dataset PlantDoc. Experimental results demonstrated our method reported respective classification accuracies of 88.32%, 89.95%, and 89.75% along with F1-scores of 88.20%, 89.24%, and 89.13% on three datasets. More importantly, the proposed architecture not only improved the classification accuracy but also promised model efficiency with low complexity, which is beneficial for precision agricultural applications. |
| first_indexed | 2024-03-10T01:00:28Z |
| format | Article |
| id | doaj.art-3c8142bbdea0422c8891975bdbbce53f |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-10T01:00:28Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-3c8142bbdea0422c8891975bdbbce53f2023-11-23T14:34:56ZengMDPI AGAgriculture2077-04722022-09-01129149910.3390/agriculture12091499Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease ClassificationXin Zuo0Jiao Chu1Jifeng Shen2Jun Sun3School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Electronic and Informatics Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Electronic and Informatics Engineering, Jiangsu University, Zhenjiang 212013, ChinaCombining disease categories and crop species leads to complex intra-class and inter-class differences. Significant intra-class difference and subtle inter-class difference pose a great challenge to high-precision crop disease classification tasks. To this end, we propose a multi-granularity feature aggregation method for accurately identifying disease types and crop species as well as better understanding the disease-affected regions implicitly. Specifically, in order to capture fine-grained discriminating clues to disease categories, we first explored the pixel-level spatial self-attention to model the pair-wise semantic relations. Second, we utilized the block-level channel self-attention to enhance the feature-discriminative ability of different crop species. Finally, we used a spatial reasoning module to model the spatial geometric relationship of the image patches sequentially, such that the feature-discriminative ability of characterizing both diseases and species is further improved. The proposed model was verified on the PDR2018 dataset, the FGVC8 dataset, and the non-lab dataset PlantDoc. Experimental results demonstrated our method reported respective classification accuracies of 88.32%, 89.95%, and 89.75% along with F1-scores of 88.20%, 89.24%, and 89.13% on three datasets. More importantly, the proposed architecture not only improved the classification accuracy but also promised model efficiency with low complexity, which is beneficial for precision agricultural applications.https://www.mdpi.com/2077-0472/12/9/1499crop disease identificationfine-grained classificationmulti-granularity featureself-attention mechanism |
| spellingShingle | Xin Zuo Jiao Chu Jifeng Shen Jun Sun Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification Agriculture crop disease identification fine-grained classification multi-granularity feature self-attention mechanism |
| title | Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification |
| title_full | Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification |
| title_fullStr | Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification |
| title_full_unstemmed | Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification |
| title_short | Multi-Granularity Feature Aggregation with Self-Attention and Spatial Reasoning for Fine-Grained Crop Disease Classification |
| title_sort | multi granularity feature aggregation with self attention and spatial reasoning for fine grained crop disease classification |
| topic | crop disease identification fine-grained classification multi-granularity feature self-attention mechanism |
| url | https://www.mdpi.com/2077-0472/12/9/1499 |
| work_keys_str_mv | AT xinzuo multigranularityfeatureaggregationwithselfattentionandspatialreasoningforfinegrainedcropdiseaseclassification AT jiaochu multigranularityfeatureaggregationwithselfattentionandspatialreasoningforfinegrainedcropdiseaseclassification AT jifengshen multigranularityfeatureaggregationwithselfattentionandspatialreasoningforfinegrainedcropdiseaseclassification AT junsun multigranularityfeatureaggregationwithselfattentionandspatialreasoningforfinegrainedcropdiseaseclassification |