论文标题
通过应用于新型柑橘虫害基准的激活图指导的弱监督学习
Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark
论文作者
论文摘要
害虫和疾病是农业生产损失的相关因素，因此促进了对预防和检测其因果剂的巨大投资。在许多国家，综合有害生物管理是预防和减轻柑橘作物害虫和疾病造成的损害的最广泛使用的过程。但是，它的结果是由视觉检查果园以识别疾病症状，昆虫和螨虫害虫的人类所记住的。在这种情况下，我们设计了一个以显着性图指导的弱监督学习过程，以自动选择图像中感兴趣的区域，从而大大减少注释任务。此外，我们创建了一个由阳性样品（六类螨虫）和负样品组成的大柑橘虫害基准。在两个大数据集上进行的实验表明，我们的结果对于农业领域中的有害生物和疾病分类问题非常有前途。
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.
