Mingle Xu ^1* Ji E. Park ¹ Jaehwan Lee ¹ Jucheng Yang ² Sook Yoon ³

• ¹ Jeonbuk National University, Jeonju, Republic of Korea
• ² Tianjin University of Science and Technology, Tianjin, China
• ³ Mokpo National University, Muan, Republic of Korea

Although plant disease recognition has witnessed a significant improvement with deep learning in recent years, a common observation is that current deep learning methods with decent performance tend to suffer in real-world applications. We argue that this illusion essentially comes from the fact that current plant disease recognition datasets cater to deep learning methods and are far from real scenarios. Mitigating this illusion fundamentally requires an interdisciplinary perspective from both plant disease and deep learning, and a core question arises. What are the characteristics of a desired dataset? This paper aims to provide a perspective for this question. First, we present a taxonomy to describe potential plant disease datasets, which provides a bridge for the two research fields. We then give several directions for making future datasets, such as creating challenge-oriented datasets. We believe that our paper will contribute to making datasets to achieve the ultimate objective, deploying deep learning in real-world applications of plant disease recognition. To facilitate the community, our project is public with the information of relevant public datasets.