Uncovering the Bias in Facial Expressions

Abstract

Over the past decades the machine and deep learning community has celebrated great achievements in challenging tasks such as image classification. The deep architecture of artificial neural networks together with the plenitude of available data makes it possible to describe highly complex relations. Yet, it is still impossible to fully capture what the deep learning model has learned and to verify that it operates fairly and without creating bias, especially in critical tasks, for instance those arising in the medical field. One example for such a task is the detection of distinct facial expressions, called Action Units, in facial images. Considering this specific task, our research aims to provide transparency regarding bias, specifically in relation to gender and skin color. We train a neural network for Action Unit classification and analyze its performance quantitatively based on its accuracy and qualitatively based on heatmaps. A structured review of our results indicates that we are able to detect bias. Even though we cannot conclude from our results that lower classification performance emerged solely from gender and skin color bias, these biases must be addressed, which is why we end by giving suggestions on how the detected bias can be avoided.

arXiv commentAccepted at the Kolloquium Forschende Frauen 2020 - published in "Gender in Gesellschaft 4.0: Beiträge Bamberger Nachwuchswissenschaftlerinnen(2021)"

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
• No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
• Residual Unfairness in Fair Machine Learning from Prejudiced Data
• Understanding and Comparing Deep Neural Networks for Age and Gender Classification
• Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
• SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning

Cited by in corpus (2)

• Gender Stereotyping Impact in Facial Expression Recognition
• Less can be more: representational vs. stereotypical gender bias in facial expression recognition