Diagnosing Gender Bias in Image Recognition Systems

By Carsten Schwemmer, C. Knight, Emily Bello-Pardo, Stan Oklobdzija, Martijn Schoonvelde, Jeffrey W. Lockhart. 2018

Image recognition systems offer the promise to learn from images at scale without requiring expert knowledge. However, past research suggests that machine learning systems often produce biased output. In this article, we evaluate potential gender biases of commercial image recognition platforms using photographs of U.S. members of Congress and a large number of Twitter images posted by these politicians. Our crowdsourced validation shows that commercial image recognition systems can produce labels that are correct and biased at the same time as they selectively report a subset of many possible true labels. We find that images of women received three times more annotations related to physical appearance. Moreover, women in images are recognized at substantially lower rates in comparison with men. We discuss how encoded biases such as these affect the visibility of women, reinforce harmful gender stereotypes, and limit the validity of the insights that can be gathered from such data.

Subfields: Computer Vision and Pattern Recognition, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In AI Ethics, Fairness & Society

Citations in the corpus

Understanding and Evaluating Racial Biases in Image Captioning (2021, background): “Under the framework of representational harms [14, 6], there is commonly a lack of representation [16, 74] and stereotyped portrayal [17, 62, 54, 65] of certain marginalized demographic groups.”
Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications (2021, background): “[19] to test how CLIP treated images of men and women using images of Members of Congress.”