Jujube is a significant economic crop in Xinjiang, China and its quality grading is the key link in the process of its storage, processing and distribution. However, there is a considerable error in the current jujube quality grading methods mainly due to the imbalanced data. Recently, Generative Adversarial Network (GAN), a novel data augmentation technology, has provided a promising solution to address data imbalance. Nevertheless, traditional GANs currently suffer from unstable training and poor generation quality. A new GAN model (named Jujube-GAN) is proposed for jujube data augmentation. In the Jujube-GAN, the self-attention mechanism is embedded into the generator and vectorising the scalar output of the discriminator stabilises the model and improves the quality of generated jujube images. The experiment result demonstrated that Jujube-GAN could synthesise higher quality images compared to traditional GANs, with lower Frechet Inception Distance (FID) scores of 63.18, 55.24 and 51.35 for three types of defective jujube images. Furthermore, the classification model achieved 13.27% increasing in the F1 score after data augmentation by Jujube-GAN. The data augmentation method proposed in this paper provides a fresh perspective and opens up possibilities for addressing data imbalance issues in other plant sciences.