Study Creates Ai Model For Effectively Reducing Biases In Dataset

Prof. Park’s research group has developed a novel image translation model that can extract and combine information about the contents of an input image and textures from a separate domain. This model is trained to use both error functions for spatial self-similarity and texture co-occurrence to store information on not only the contents of input photos but also the texture of the new domain. This model is expected to help with breakthroughs in self-driving cars, content development, and medicine.