APPARATUS AND METHOD OF DATA GENERATION FOR OBJECT DETECTION BASED ON GENERATIVE ADVERSARIAL NETWORKS

摘要

An objective of the present invention is to increase the object recognition performance compared to that of an existing object recognition algorithm. To this end, according to the present invention, an apparatus for generating data based on a generative adversarial neural network (GAN) comprises: a first generator for receiving input data to generate a first fake image; and a first discriminator for receiving a first real image and the first fake image generated by the first generator and discriminating whether an image is fake or real.