Modified CycleGAN for the synthesization of samples for wheat head segmentation
This addresses the tedious and expensive process of creating annotated datasets for agricultural image analysis, though it is incremental as it adapts existing GAN methods to a specific domain.
The researchers tackled the problem of limited annotated data for deep learning by generating a synthetic dataset using a modified CycleGAN to bridge the domain gap between simulated and real images, resulting in a wheat head segmentation model that achieved Dice scores of 83.4% on an internal dataset and up to 83.6% on external datasets.
Deep learning models have been used for a variety of image processing tasks. However, most of these models are developed through supervised learning approaches, which rely heavily on the availability of large-scale annotated datasets. Developing such datasets is tedious and expensive. In the absence of an annotated dataset, synthetic data can be used for model development; however, due to the substantial differences between simulated and real data, a phenomenon referred to as domain gap, the resulting models often underperform when applied to real data. In this research, we aim to address this challenge by first computationally simulating a large-scale annotated dataset and then using a generative adversarial network (GAN) to fill the gap between simulated and real images. This approach results in a synthetic dataset that can be effectively utilized to train a deep-learning model. Using this approach, we developed a realistic annotated synthetic dataset for wheat head segmentation. This dataset was then used to develop a deep-learning model for semantic segmentation. The resulting model achieved a Dice score of 83.4\% on an internal dataset and Dice scores of 79.6% and 83.6% on two external Global Wheat Head Detection datasets. While we proposed this approach in the context of wheat head segmentation, it can be generalized to other crop types or, more broadly, to images with dense, repeated patterns such as those found in cellular imagery.