SynthSet: Generative Diffusion Model for Semantic Segmentation in Precision Agriculture

TL;DR

This paper presents SynthSet, a novel generative diffusion model combining DDPMs and GANs to create realistic annotated agricultural images, improving data availability for semantic segmentation in precision agriculture.

Contribution

The paper introduces a dual diffusion model architecture that synthesizes high-quality annotated agricultural data without human intervention, enhancing data diversity for segmentation tasks.

Findings

SynthSet generates realistic image-mask pairs for wheat head segmentation.

Models trained on SynthSet data perform well on external real-world datasets.

The approach can be adapted to various segmentation tasks in agriculture and other domains.

Abstract

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.