Instance-Aware Plant Disease Detection by Utilizing Saliency Map and Self-Supervised Pre-Training

Abstract

Plant disease detection is essential for optimizing agricultural productivity and crop quality. With the recent advent of deep learning and large-scale plant disease datasets, many studies have shown high performance of supervised learning-based plant disease detectors. However, these studies still have limitations due to two aspects. First, labeling cost and class imbalance problems remain challenging in supervised learning-based methods. Second, plant disease datasets are either unstructured or weakly-unstructured and the shapes of leaves and diseased areas on them are variable, rendering plant disease detection even more challenging. To overcome these limitations, we propose an instance-aware unsupervised plant disease detector, which leverages normalizing flows, a visual saliency map and positional encodings. A novel way to explicitly combine these methods is the proposed model, in which the focus is on reducing background noise. In addition, to better fit the model to the plant disease detection domain and to enhance feature representation, a feature extractor is pre-trained in a self-supervised learning manner using only unlabeled data. In our extensive experiments, it is shown that the proposed approach achieves state-of-the-art performance on widely-used datasets, such as BRACOL (Weakly-unstructured) and PlantVillage (Unstructured), regardless of whether the dataset is weakly-structured or unstructured.

Enhancing land cover maps with optical time series and ambiguous loss function

“…[16][17][18] A detailed analysis 15 of current SSL solutions and their benefits for agriculture showed the advantages and performance improvements based on different use cases such as weed or crop-type classification, plant disease detection or nitrogen status prediction. For example, Kim et al 19 investigated plant disease detection using SSL and CNN's and achieved up to 14.3% higher accuracies with pre-training. 15 Prediction of nitrogen status, an essential parameter for precision agriculture, was explored using SSL, UAV data, and a Vision Transformer, and outperformed the supervised model with an overall accuracy of 96.2% compared to 94.4%.…”

Three-Dimensional Structure Measurement for Potted Plant Based on Millimeter-Wave Radar

“…The combination of advanced sensing technologies such as computer vision [9,10] and LIDAR (light detection and ranging) [11,12] with conventional agricultural equipment has led to the emergence of a new generation of modern precision spraying machines and devices [13]. The agricultural environment is dynamic and uncertain, which makes it challenging to collect target information.…”