Search Results for author: Dora Zhao

Found 4 papers, 2 papers with code

Men Also Do Laundry: Multi-Attribute Bias Amplification

no code implementations21 Oct 2022 Dora Zhao, Jerone T. A. Andrews, Alice Xiang

We show models can learn to exploit correlations with respect to multiple attributes (e. g., {$\texttt{computer}$, $\texttt{keyboard}$}), which are not accounted for by current metrics.

Gender Artifacts in Visual Datasets

no code implementations18 Jun 2022 Nicole Meister, Dora Zhao, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky

Gender biases are known to exist within large-scale visual datasets and can be reflected or even amplified in downstream models.

Understanding and Evaluating Racial Biases in Image Captioning

1 code implementation ICCV 2021 Dora Zhao, Angelina Wang, Olga Russakovsky

Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments.

Image Captioning Visual Reasoning

Cannot find the paper you are looking for? You can Submit a new open access paper.