Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark
This work addresses pest detection in agriculture, which is crucial for reducing production losses, but it is incremental as it applies existing weakly supervised techniques to a new domain-specific benchmark.
The paper tackles the problem of pest and disease classification in citrus crops by designing a weakly supervised learning process guided by saliency maps to reduce annotation effort, and it reports promising results on two large datasets.
Pests and diseases are relevant factors for production losses in agriculture and, therefore, promote a huge investment in the prevention and detection of its causative agents. In many countries, Integrated Pest Management is the most widely used process to prevent and mitigate the damages caused by pests and diseases in citrus crops. However, its results are credited by humans who visually inspect the orchards in order to identify the disease symptoms, insects and mite pests. In this context, we design a weakly supervised learning process guided by saliency maps to automatically select regions of interest in the images, significantly reducing the annotation task. In addition, we create a large citrus pest benchmark composed of positive samples (six classes of mite species) and negative samples. Experiments conducted on two large datasets demonstrate that our results are very promising for the problem of pest and disease classification in the agriculture field.