Unsupervised Transfer Learning for Plant Anomaly Recognition
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.
Abstract
Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.
참고문헌 (17)
- Pan, Sinno Jialin, "A survey on transfer learning", IEEE Transactions on knowledge and data engineering, 22(10), pp.1345~1359 (2010)
- Mohanty, Sharada P., "Using deep learning for image-based plant disease detection", Frontiers in plant science (2016)
- Zhao, Xue, "Identification method of vegetable diseases based on transfer learning and attention mechanism", Computers and Electronics in Agriculture, 193 (2022)
- Li, Yang, "Semi-supervised few-shot learning approach for plant diseases recognition", Plant Methods, 17(68) (2021)
- Deng, Jia, "Imagenet: A large-scale hierarchical image database", 2009 IEEE conference on computer vision and pattern recognition. Ieee (2009)
- He, Kaiming, "Masked autoencoders are scalable vision learners", arXiv preprint arXiv:2111.06377, ~ (2021)
- Hughes, David, "An open access repository of images on plant health to enable the development of mobile disease diagnostics", arXiv preprint arXiv : 1511. 08060, ~ (2015)
- Sethy, Prabira Kumar, "Deep feature based rice leaf disease identification using support vector machine", Computers and Electronics in Agriculture, 175 (2020)
- Dosovitskiy, Alexey, "An Image is Worth 16x16 Words : Transformers for Image Recognition at Scale", International Conference on Learning Representations (2020)
- Liu, Ze, "Swin transformer : Hierarchical vision transformer using shifted windows", Proceedings of the IEEE, 2021, ~
- Xu, Mingle, "Style-Consistent Image Translation : A Novel Data Augmentation Paradigm to Improve Plant Disease Recognition", Frontiers in Plant Science, 12 (2022)
- Fuentes, Alvaro, "A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition", Sensors, 17(9) (2017)
- Argüeso, David, "Few-Shot Learning approach for plant disease classification using images taken in the field", Computers and Electronics in Agriculture, 175 (2020)
- Liang, Xihuizi, "Few-shot cotton leaf spots disease classification based on metric learning", Plant Methods, 17(1) (2021)
- Haseeb Nazki, "Image-to-Image Translation with GAN for Synthetic Data Augmentation in Plant Disease Datasets", 스마트미디어저널, 8(2), pp.46~57 (2019), (사)한국스마트미디어학회[DOI]
- 문인식, "농작물을 위한 드론 분무 농약 살포의 3차원 분석에 관한 연구", 스마트미디어저널, 9(4), pp.176~186 (2020), (사)한국스마트미디어학회[DOI]
- 이기성, "2차원 변환과 CNN 딥러닝 기반 음향 인식 시스템에 관한 연구", 스마트미디어저널, 11(1), pp.31~37 (2022), (사)한국스마트미디어학회[DOI]