Class‐specific data augmentation for plant stress classification
Abstract Data augmentation is a powerful tool for improving deep learning‐based image classifiers for plant stress identification and classification. However, selecting an effective set of augmentations from a large pool of candidates remains a key challenge, particularly in imbalanced and confoundi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Plant Phenome Journal |
| Online Access: | https://doi.org/10.1002/ppj2.20112 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850253499276722176 |
|---|---|
| author | Nasla Saleem Aditya Balu Talukder Zaki Jubery Arti Singh Asheesh K. Singh Soumik Sarkar Baskar Ganapathysubramanian |
| author_facet | Nasla Saleem Aditya Balu Talukder Zaki Jubery Arti Singh Asheesh K. Singh Soumik Sarkar Baskar Ganapathysubramanian |
| author_sort | Nasla Saleem |
| collection | DOAJ |
| description | Abstract Data augmentation is a powerful tool for improving deep learning‐based image classifiers for plant stress identification and classification. However, selecting an effective set of augmentations from a large pool of candidates remains a key challenge, particularly in imbalanced and confounding datasets. We propose an approach for automated class‐specific data augmentation using a genetic algorithm. We demonstrate the utility of our approach on soybean [Glycine max (L.) Merr] stress classification where symptoms are observed on leaves; a particularly challenging problem due to confounding classes in the dataset. Our approach yields substantial performance, achieving a mean‐per‐class accuracy of 97.61% and an overall accuracy of 98% on the soybean leaf stress dataset. Our method significantly improves the accuracy of the most challenging classes, with notable enhancements from 83.01% to 88.89% and from 85.71% to 94.05%, respectively. A key observation we make in this study is that high‐performing augmentation strategies can be identified in a computationally efficient manner. We fine‐tune only the linear layer of the baseline model with different augmentations, thereby reducing the computational burden associated with training classifiers from scratch for each augmentation policy while achieving exceptional performance. This research represents an advancement in automated data augmentation strategies for plant stress classification, particularly in the context of confounding datasets. Our findings contribute to the growing body of research in tailored augmentation techniques and their potential impact on disease management strategies, crop yields, and global food security. The proposed approach holds the potential to enhance the accuracy and efficiency of deep learning‐based tools for managing plant stresses in agriculture. |
| format | Article |
| id | doaj-art-bc7e71f34cf34de8a2aec6d6b8d19877 |
| institution | OA Journals |
| issn | 2578-2703 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Plant Phenome Journal |
| spelling | doaj-art-bc7e71f34cf34de8a2aec6d6b8d198772025-08-20T01:57:21ZengWileyPlant Phenome Journal2578-27032024-12-0171n/an/a10.1002/ppj2.20112Class‐specific data augmentation for plant stress classificationNasla Saleem0Aditya Balu1Talukder Zaki Jubery2Arti Singh3Asheesh K. Singh4Soumik Sarkar5Baskar Ganapathysubramanian6Department of Mechanical Engineering Iowa State University Ames Iowa USADepartment of Mechanical Engineering Iowa State University Ames Iowa USADepartment of Mechanical Engineering Iowa State University Ames Iowa USADepartment of Agronomy Iowa State University Ames Iowa USADepartment of Agronomy Iowa State University Ames Iowa USADepartment of Mechanical Engineering Iowa State University Ames Iowa USADepartment of Mechanical Engineering Iowa State University Ames Iowa USAAbstract Data augmentation is a powerful tool for improving deep learning‐based image classifiers for plant stress identification and classification. However, selecting an effective set of augmentations from a large pool of candidates remains a key challenge, particularly in imbalanced and confounding datasets. We propose an approach for automated class‐specific data augmentation using a genetic algorithm. We demonstrate the utility of our approach on soybean [Glycine max (L.) Merr] stress classification where symptoms are observed on leaves; a particularly challenging problem due to confounding classes in the dataset. Our approach yields substantial performance, achieving a mean‐per‐class accuracy of 97.61% and an overall accuracy of 98% on the soybean leaf stress dataset. Our method significantly improves the accuracy of the most challenging classes, with notable enhancements from 83.01% to 88.89% and from 85.71% to 94.05%, respectively. A key observation we make in this study is that high‐performing augmentation strategies can be identified in a computationally efficient manner. We fine‐tune only the linear layer of the baseline model with different augmentations, thereby reducing the computational burden associated with training classifiers from scratch for each augmentation policy while achieving exceptional performance. This research represents an advancement in automated data augmentation strategies for plant stress classification, particularly in the context of confounding datasets. Our findings contribute to the growing body of research in tailored augmentation techniques and their potential impact on disease management strategies, crop yields, and global food security. The proposed approach holds the potential to enhance the accuracy and efficiency of deep learning‐based tools for managing plant stresses in agriculture.https://doi.org/10.1002/ppj2.20112 |
| spellingShingle | Nasla Saleem Aditya Balu Talukder Zaki Jubery Arti Singh Asheesh K. Singh Soumik Sarkar Baskar Ganapathysubramanian Class‐specific data augmentation for plant stress classification Plant Phenome Journal |
| title | Class‐specific data augmentation for plant stress classification |
| title_full | Class‐specific data augmentation for plant stress classification |
| title_fullStr | Class‐specific data augmentation for plant stress classification |
| title_full_unstemmed | Class‐specific data augmentation for plant stress classification |
| title_short | Class‐specific data augmentation for plant stress classification |
| title_sort | class specific data augmentation for plant stress classification |
| url | https://doi.org/10.1002/ppj2.20112 |
| work_keys_str_mv | AT naslasaleem classspecificdataaugmentationforplantstressclassification AT adityabalu classspecificdataaugmentationforplantstressclassification AT talukderzakijubery classspecificdataaugmentationforplantstressclassification AT artisingh classspecificdataaugmentationforplantstressclassification AT asheeshksingh classspecificdataaugmentationforplantstressclassification AT soumiksarkar classspecificdataaugmentationforplantstressclassification AT baskarganapathysubramanian classspecificdataaugmentationforplantstressclassification |