Current dataset collection methods typically scrape large amounts of data from the web.
Second, we find that concepts in the probe dataset are often less salient and harder to learn than the classes they claim to explain, calling into question the correctness of the explanations.
Gender biases are known to exist within large-scale visual datasets and can be reflected or even amplified in downstream models.
Specifically, we develop a novel explanation framework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) that decomposes a model's prediction into two parts: one that is explainable through a linear combination of the semantic attributes, and another that is dependent on the set of uninterpretable features.
In this work, we grapple with questions that arise along three stages of the machine learning pipeline when incorporating intersectionality as multiple demographic attributes: (1) which demographic attributes to include as dataset labels, (2) how to handle the progressively smaller size of subgroups during model training, and (3) how to move beyond existing evaluation metrics when benchmarking model fairness for more subgroups.
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable.
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world.