Discover the Unknown Biased Attribute of an Image Classifier

Understand

Recent works find that AI algorithms learn biases from data.

• Therefore, it is urgent and vital to identify biases in AI algorithms.
• However, the previous bias identification pipeline overly relies on human experts to conjecture potential biases (e.g., gender), which may neglect other underlying biases not realized by humans.
• To help human experts better find the AI algorithms' biases, we study a new problem in this work -- for a classifier that predicts a target attribute of the input image, discover its unknown biased attribute.