Men Also Do Laundry: Multi-Attribute Bias Amplification

Dora Zhao

Jerone T. A. Andrews

Alice Xiang

ICML 2023



As computer vision systems become more widely deployed, there is increasing concern from both the research community and the public that these systems are not only reproducing but amplifying harmful social biases. The phenomenon of bias amplification, which is the focus of this work, refers to models amplifying inherent training set biases at test time. Existing metrics measure bias amplification with respect to single annotated attributes (e.g., 𝚌𝚘𝚖𝚙𝚞𝚝𝚎𝚛). However, several visual datasets consist of images with multiple attribute annotations. We show models can learn to exploit correlations with respect to multiple attributes (e.g., {𝚌𝚘𝚖𝚙𝚞𝚝𝚎𝚛, 𝚔𝚎𝚢𝚋𝚘𝚊𝚛𝚍}), which are not accounted for by current metrics. In addition, we show current metrics can give the erroneous impression that minimal or no bias amplification has occurred as they involve aggregating over positive and negative values. Further, these metrics lack a clear desired value, making them difficult to interpret. To address these shortcomings, we propose a new metric: Multi-Attribute Bias Amplification. We validate our proposed metric through an analysis of gender bias amplification on the COCO and imSitu datasets. Finally, we benchmark bias mitigation methods using our proposed metric, suggesting possible avenues for future bias mitigation

Related Publications

Ethical Considerations for Responsible Data Curation

NeurIPS, 2023
Jerone Andrews, Dora Zhao, William Thong, Apostolos Modas, Orestis Papakyriakopoulos, Alice Xiang

Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models. HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for comprehensive fairness and robustnes…

Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color

ICCV, 2023
William Thong, Przemyslaw Joniak*, Alice Xiang

This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. While…

Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data

AIES, 2023
Keziah Naggita*, Julienne LaChance, Alice Xiang

Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centri…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.