SynthSet: Generative Diffusion Model for Semantic Segmentation in Precision Agriculture
This addresses data scarcity for semantic segmentation tasks in precision agriculture, offering a method that can be adapted to other domains, though it is incremental as it builds on existing diffusion and GAN techniques.
The paper tackles data scarcity in semantic segmentation for precision agriculture by developing a generative diffusion model to synthesize annotated agricultural data, showing that models trained on this synthetic data achieve promising performance on real wheat field datasets.
This paper introduces a methodology for generating synthetic annotated data to address data scarcity in semantic segmentation tasks within the precision agriculture domain. Utilizing Denoising Diffusion Probabilistic Models (DDPMs) and Generative Adversarial Networks (GANs), we propose a dual diffusion model architecture for synthesizing realistic annotated agricultural data, without any human intervention. We employ super-resolution to enhance the phenotypic characteristics of the synthesized images and their coherence with the corresponding generated masks. We showcase the utility of the proposed method for wheat head segmentation. The high quality of synthesized data underscores the effectiveness of the proposed methodology in generating image-mask pairs. Furthermore, models trained on our generated data exhibit promising performance when tested on an external, diverse dataset of real wheat fields. The results show the efficacy of the proposed methodology for addressing data scarcity for semantic segmentation tasks. Moreover, the proposed approach can be readily adapted for various segmentation tasks in precision agriculture and beyond.