Few-shot vegetable disease recognition model based on image text collaborative representation learning

Wang, Chun‐Shan; Zhou, Ji; Zhao, Chunjiang; Li, Jiuxi; Teng, Guifa; Wu, Haiyuan

doi:10.1016/j.compag.2021.106098

Cited by 32 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results suggest that the cross-modal fusion model outperformed all singlemodal identification models. In terms of cross-modal feature fusion, Zhao et al (2020) and Wang et al (2021) applied different models to map the disease features in the images and texts into independent feature spaces respectively, and then fused the probabilities of the identification results of each modality. In this paper, the disease features in the images and texts were directly mapped to a unified feature space so as to realize the feature fusion between cross-modal data.…”

Section: Discussionmentioning

confidence: 99%

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion

et al. 2022

Self Cite

View full text Add to dashboard Cite

In view of the differences in appearance and the complex backgrounds of crop diseases, automatic identification of field diseases is an extremely challenging topic in smart agriculture. To address this challenge, a popular approach is to design a Deep Convolutional Neural Network (DCNN) model that extracts visual disease features in the images and then identifies the diseases based on the extracted features. This approach performs well under simple background conditions, but has low accuracy and poor robustness under complex backgrounds. In this paper, an end-to-end disease identification model composed of a disease-spot region detector and a disease classifier (YOLOv5s + BiCMT) was proposed. Specifically, the YOLOv5s network was used to detect the disease-spot regions so as to provide a regional attention mechanism to facilitate the disease identification task of the classifier. For the classifier, a Bidirectional Cross-Modal Transformer (BiCMT) model combining the image and text modal information was constructed, which utilizes the correlation and complementarity between the features of the two modalities to achieve the fusion and recognition of disease features. Meanwhile, the problem of inconsistent lengths among different modal data sequences was solved. Eventually, the YOLOv5s + BiCMT model achieved the optimal results on a small dataset. Its Accuracy, Precision, Sensitivity, and Specificity reached 99.23, 97.37, 97.54, and 99.54%, respectively. This paper proves that the bidirectional cross-modal feature fusion by combining disease images and texts is an effective method to identify vegetable diseases in field environments.

show abstract

Section: Discussionmentioning

confidence: 99%

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…At present, few-shot learning is also the most widely used in agricultural and plant properties for the identification of plant diseases. For example, Liang et al Used the few-shot learning method based on metric learning to identify cotton leaf spots [ 19 ], Wang et al proposed multi-mode collaborative representation learning based on disease images and disease texts to solve the problem of vegetable disease identification under complex background [ 52 ], Argüeso et al also used the few-shot model based on metric learning to identify 38 plant diseases in the dataset PlantVillage [ 53 ], and Zhong et al used the conditional adversary automatic encoder (CAAE) to identify citrus golden grape diseases [ 54 ]. These studies only use a small number of labeled samples to achieve satisfactory results, so that the identification of plant diseases will no longer rely on expert experience and realize automatic identification in the future.…”

Section: Applicationsmentioning

confidence: 99%

A survey of few-shot learning in smart agriculture: developments, applications, and challenges

Yang

Guo

et al. 2022

Plant Methods

View full text Add to dashboard Cite

With the rise of artificial intelligence, deep learning is gradually applied to the field of agriculture and plant science. However, the excellent performance of deep learning needs to be established on massive numbers of samples. In the field of plant science and biology, it is not easy to obtain a large amount of labeled data. The emergence of few-shot learning solves this problem. It imitates the ability of humans’ rapid learning and can learn a new task with only a small number of labeled samples, which greatly reduces the time cost and financial resources. At present, the advanced few-shot learning methods are mainly divided into four categories based on: data augmentation, metric learning, external memory, and parameter optimization, solving the over-fitting problem from different viewpoints. This review comprehensively expounds on few-shot learning in smart agriculture, introduces the definition of few-shot learning, four kinds of learning methods, the publicly available datasets for few-shot learning, various applications in smart agriculture, and the challenges in smart agriculture in future development.

show abstract

“…In livestream selling, Shandong Province has also been constantly optimizing the circulation of agricultural products. Agricultural information technologies, such as agricultural database system, agricultural decision-making system, management information system, 3S technology, expert system, global positioning system, computer network, agricultural multimedia technology, and remote communication, have emerged successively [40,41].…”

Section: Improvement Of the Agricultural Intelligence Levelmentioning

confidence: 99%

Coordination of agricultural informatization and agricultural economy development: A panel data analysis from Shandong Province, China

Sun

Zhao

2022

PLoS ONE

View full text Add to dashboard Cite

With the continuous development of the world economy, science, and technology, the era of intelligence and information is upon us. Through the implementation of the digital rural construction project in China, agriculture is developing rapidly in the direction of informatization. As a major agricultural province in China, Shandong Province has been ranked first in China for many years in terms of gross agricultural product and the import and export of agricultural products. According to the current situation of agricultural informatization in Shandong Province, this study uses relevant evaluation index data of Shandong Province from 2011 to 2019 and applies the entropy value method, coupling degree analysis model, and coupling coordination degree analysis model to deeply evaluate the mutual influence and coordination degree between the agricultural informatization level and agricultural economic development in Shandong province in each year. We identify the possible problems in the development of agricultural informatization in Shandong province. Finally, in terms of talent construction, infrastructure construction, the main role of government, policies, and farmers’ awareness of informatization, we propose some countermeasures and suggestions that are conducive to the coordinated development of agricultural informatization and the agricultural economy.

show abstract

Few-shot vegetable disease recognition model based on image text collaborative representation learning

Cited by 32 publications

References 15 publications

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion

A Vegetable Leaf Disease Identification Model Based on Image-Text Cross-Modal Feature Fusion

A survey of few-shot learning in smart agriculture: developments, applications, and challenges

Coordination of agricultural informatization and agricultural economy development: A panel data analysis from Shandong Province, China

Contact Info

Product

Resources

About