Summary: Many start-ups, academics and even corporates are struggling to get enough data. Many go as far as to generate new data from game engines. In this talk, we will explore using domain adaptation to make this data more photorealistic to minimize the gap between our training set & deployment. We will review the literature as well as look at some practical examples and pitfalls.
Bio: Jakub Langr graduated from the University of Oxford where he also taught at OU Computing Services. He has worked in data science since 2013, most recently as a Data Science Tech Lead at Filtered.com and as an R&D Data Scientist at Mudano. Jakub is a co-author of GANs in Action by Manning Publications. Jakub also designed and teaches Data Science courses at the University of Birmingham, numerous private companies and is a guest lecturer at the University of Oxford.