Domain Adaptation of Synthetic Images for Wheat Head Detection

Hartley, Zane K.J.; French, Andrew P.

Abstract

Wheat head detection is a core computer vision problem related to plant phenotyping that in recent years has seen increased interest as large-scale datasets have been made available for use in research. In deep learning problems with limited training data, synthetic data have been shown to improve performance by increasing the number of training examples available but have had limited effectiveness due to domain shift. To overcome this, many adversarial approaches such as Generative Adversarial Networks (GANs) have been proposed as a solution by better aligning the distribution of synthetic data to that of real images through domain augmentation. In this paper, we examine the impacts of performing wheat head detection on the global wheat head challenge dataset using synthetic data to supplement the original dataset. Through our experimentation, we demonstrate the challenges of performing domain augmentation where the target domain is large and diverse. We then present a novel approach to improving scores through using heatmap regression as a support network, and clustering to combat high variation of the target domain.

Citation

Hartley, Z. K., & French, A. P. (2021). Domain Adaptation of Synthetic Images for Wheat Head Detection. Plants, 10(12), Article 2633. https://doi.org/10.3390/plants10122633

• Journal Article Type: Article
• Acceptance Date: Nov 25, 2021
• Online Publication Date: Nov 30, 2021
• Publication Date: 2021-12
• Deposit Date: Jun 17, 2022
• Publicly Available Date: Jun 17, 2022
• Journal: Plants
• Electronic ISSN: 2223-7747
• Publisher: MDPI AG
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 12
• Article Number: 2633
• DOI: https://doi.org/10.3390/plants10122633
• Keywords: Plant Science; Ecology; Ecology, Evolution, Behavior and Systematics
• Public URL: https://nottingham-repository.worktribe.com/output/7024274
• Publisher URL: https://www.mdpi.com/2223-7747/10/12/2633