Abstract: The object detection method based on deep learning is widely used in industrial inspection. In order to solve the problem of insufficient industrial defect data, an improved defect data augmentation algorithm based on pip2pix is proposed. Starting from the enhancement of the generator and discriminators attention to the defect area in the image, the following improvements have been made to pix2pix:(1)Only the defect area of the entire image is used as the input of the discriminator to enhance the generators attention to the defect area. At the same time, the discriminator uses a smaller convolution kernel to extract the characteristics of the defect area. (2)Only the average generation confrontation loss of all defect regions in the image is used as the generation confrontation loss of the image, so that the network pays more attention to the defects regional feature learning. The experimental results on the industrial LED defect dataset show that the defects generated by the proposed method have more realistic visual effects, lower FID, and effectively improve the accuracy of defect detection based on the RetinaNet algorithm.

Key words: object detection, data augmentation, pix2pix, attention