Multi-modal Learning for Effective In-the-Wild Plant Disease Detection

The School of EECS is hosting the following PhD Progress Review 1 Confirmation Seminar:

Multi-modal Learning for Effective In-the-Wild Plant Disease Detection

Speaker: Tianqi Wei
Host: Prof. Helen Huang

Abstract: Plant disease recognition aims to identify disease through visual symptoms, it has a profound impact on agricultural production and food safety. Traditional deep learning methods have achieved satisfactory results in identifying plant diseases from images taken in laboratory settings, but their accuracy significantly decreases when applied to images taken in the wild due to their complexity. We have identified two main reasons for this phenomenon. Firstly, plant diseases may exhibit similar appearances across different diseases. Secondly, the same disease can manifest differently depending on factors such as infected parts and severity. In response to these challenges, we introduce multimodal learning to effectively address these problems.

Bio: Tianqi Wei is currently a PhD student at the School of Electrical Engineering and Computer Science, the University of Queensland. He received his M. InfTech at the University of Queensland in 2022. His research interests include computer vision and multi-modal learning.