IFML Public Lecture: AI for Accurate and Fair Imaging
On April 1, IFML held its inaugural public lecture, "AI For Accurate and Fair Imaging" with Alex Dimakis. The talk covered recent research into bias in AI imaging algorithms. In 2020, a deep learning generative model with groundbreaking performance was posted on the web. The model could turn low-resolution images to high-quality photos. A user uploaded a low-resolution image of President Obama and obtained an image that is now referred to as ‘White Obama’. The deep learning model was reconstructing images with predominantly white features and a heated debate arose across Twitter and other social media: Researchers at UT Austin set out to find the source of the problem and solve it. Watch a replay of the talk and read the news article: "UT Austin researchers tackle AI that created 'White Obama' image.