Detecting and Mitigating Bias in Machine Learning Image Data through Semantic Description of the Attention Mechanism: The use-case Gender Bias in Profession Prediction from Images

Machine Learning models are increasingly used to assist or replace humans in a variety of decision-making domains. However, a lot of concerns have been raised about the impact of these decisions on people’s lives. In this work we focus on two main problems. The first one is that there might be discrimination between different groups of people...