From Laboratory to Field: Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild

Abstract

Plant disease recognition is of vital importance to monitor plant development and predicting crop production. However, due to data degradation caused by different conditions of image acquisition, e.g., laboratory vs. field environment, machine learning-based recognition models generated within a specific dataset (source domain) tend to lose their validity when generalized to a novel dataset (target domain). To this end, domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains. In this paper, we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization, namely, Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification (MSUN). Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial training. Specifically, MSUN comprises multirepresentation, subdomain adaptation modules and auxiliary uncertainty regularization. The multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source domain. This effectively alleviates the problem of large interdomain discrepancy. Subdomain adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass variation. Finally, the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain transfer. MSUN was experimentally validated to achieve optimal results on the PlantDoc, Plant-Pathology, Corn-Leaf-Diseases, and Tomato-Leaf-Diseases datasets, with accuracies of 56.06%, 72.31%, 96.78%, and 50.58%, respectively, surpassing other state-of-the-art domain adaptation techniques considerably.

Embracing limited and imperfect training datasets: opportunities and challenges in plant disease recognition using deep learning

“…Second, the distribution of the training dataset is gradually approaching that of the test dataset when the training dataset becomes larger, supporting a better test performance. For example, a model trained with images captured in laboratories is not expected to be effective when tested with images captured on farms ( Guth et al., 2023 ; Wu et al., 2023 ).…”

“…A frequent performance drop occurs when a model is trained on a dataset from a particular scenario but is further tested on data from a different scenario. A common scenario, for example, is that the training dataset is collected in one place by one person and the test dataset is collected in another place with different infrastructures and illumination by another person with their individual habit of taking pictures, such as training in the images collected in the laboratory and testing in the real world ( Guth et al., 2023 ; Wu et al., 2023 ).…”

“…The generalization capabilities of CNNs are investigated to learn the clear patterns from lab conditions that are to be detected again under new and more complex field conditions while avoiding overfitting ( Guth et al., 2023 ). The important insight derived from this is that, in order to create useful tools for disease detection and classification using deep learning for image analysis, it is crucial to develop a final product that can handle a wide range of images from various crop conditions and locations, including inter-class and intra-class variations ( Wu et al., 2023 ). This requires carefully designed datasets with a large number of image samples that can accommodate the significant variability in crop conditions in different areas.…”

Explore Innovative Depth Vision Models with Domain Adaptation

“…In plant disease recognition, Fuentes et al [14] proposed open-set adaptation and cross-domain adaptation methods to enhance tomato disease recognition using unlabeled data. Additionally, Wu et al [15] achieved cross-domain recognition of wild plant diseases. In robotics, Magistri et al [16] introduced Unsupervised Domain Adaptation (UDA) techniques for semantic segmentation, enhancing the adaptability of agricultural robots to better perceive and understand different environments.…”

A Multiscale Point-Supervised Network for Counting Maize Tassels in the Wild

“…With the rapid development of deep learning, deep convolutional neural networks (CNNs) have made unprecedented progress in computer vision algorithms for agriculture such as disease recognition and detection [ 10 , 11 , 45 ], crop land segmentation [ 12 ], and weed mapping [14] . CNNs have also been applied for counting tasks in crops and plants, which can be categorized into detect-and-count (DC), direct counting regression (DR), and density map estimation.…”