This event has ended. Visit the official site or create your own event on Sched.
Tom Tom champions civic innovation, creativity, and entrepreneurship in America’s hometowns.

[Back to Tom Tom Festival]
Back To Schedule
Thursday, April 11 • 2:50pm - 3:20pm
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations

Log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
In this work we analyze visual recognition tasks such as object and action recognition, and demonstrate the extent to which these tasks are correlated with features corresponding to a protected variable such as gender. We introduce the concept of “natural leakage” to measure the intrinsic reliance of a task on a protected variable. We further show that machine learning models of visual recognition trained for these tasks tend to exacerbate the reliance on gender features. To address this, we use adversarial training to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network. Experiments on two datasets: the COCO dataset (objects), and the imSitu dataset (actions), show reductions in the extent to which models rely on gender features while maintaining most of the accuracy of the original models. These results even surpass a strong baseline that blurs or removes people from images using ground-truth annotations. Moreover, we provide convincing interpretable visual evidence through an autoencoder-augmented model showing that this approach is performing semantically meaningful removal of gender features, and thus can also be used to remove gender attributes directly from images.

You need this ticket from Eventbrite to sign up: Applied Machine Learning Conference.

avatar for Tianlu Wang

Tianlu Wang

Graduate Student, University of Virginia, Department of Computer Science
Tianlu Wang is a Ph.D. student at the Department of Computer Science at the University of Virginia. She has been working with Prof. Vicente Ordóñez Román since Fall 2016. Her research focus lies at the intersection of computer vision and natural language processing. More recently... Read More →


Thursday April 11, 2019 2:50pm - 3:20pm EDT
Violet Crown: Theater 3 200 W Main St, Charlottesville, VA 22902, USA