基于改进DCGAN轮胎缺陷图像生成方法

针对深度卷积生成对抗网络的数据扩充方法存在生成图像质量差、模型框架不稳定、模型收敛速度慢等问题，提出一种改进DCGAN轮胎缺陷图像生成模型。将残差网络和注意力机制嵌入到DCGAN模型中，提升模型特征的提取能力；同时摒弃DCGAN损失函数JS散度，使用带有梯度惩罚项的Wasserstein距离，提高模型训练的稳定性。实验结果表明，使用给定模型生成的轮胎缺陷图像质量优于使用DCGAN，WGAN，CGAN与SAGAN所生成图像，其平均FID值可以达到116.28，最小FID值可以达到84.94。所提出的模型可以稳定生成质量更好的轮胎缺陷图像，为轮胎缺陷样本数据集的扩充提供了一种有效途径，有助于有效解决深度学习在缺陷检测领域发展所面临的小样本问题。

A method for generating tire defect images based on improved DCGAN

An improved DCGAN tire defect image generation model was proposed to solve the problems of poor image quality, unstable model frame and slow model convergence in the data expansion method of deep convolutional generative adversarial network. The residual network and attention mechanism were embedded in DCGAN model to improve the feature extraction ability of the model. At the same time, the DCGAN loss function JS divergence was abandoned and Wasserstein distance with gradient penalty term was used to improve the stability of model training. The experimental results show that the quality of tire defect images generated by this model is better than that generated by DCGAN, WGAN, CGAN and SAGAN,with an average FID value of 11628 and a minimum FID value of 8494. The proposed model can stably generate tire defect images with better quality, which provides an effective way for expanding tire defect sample dataset and alleviates the problem of small sample in the development of deep learning in the field of defect detection.