Measuring algorithmic bias in face analysis — towards an experimental approach

23rd February 2021

 

Lecture by Prof. Pietro Perona Measuring algorithmic bias in face analysis — towards an experimental approach

Abstract

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational datasets, are inadequate for this task because they conflate algorithmic bias with dataset bias. To address this problem I will propose experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e.g., gender and skin tone, in order to reveal causal links between attribute variation and performance change. The method is based on generating synthetic “transects” of matched sample images that are designed to differ along specific attributes while leaving other attributes constant. A crucial aspect of our approach is relying on the perception of human observers, both to guide manipulations, and to measure algorithmic bias. Besides allowing the measurement of algorithmic bias, synthetic transects have other advantages with respect to observational datasets: sampling  attributes more evenly, allowing for more straightforward bias analysis on minority and intersectional groups, enabling prediction of bias in new scenarios, reducing ethical and legal challenges, and they are economical and fast to obtain, helping make bias testing affordable and widely available. The method is validated by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms. The two methods reach different conclusions. While the observational method reports gender and skin color biases, the experimental method reveals biases due to gender, hair length, age, and facial hair.

Short CV

Professor Perona is the Allen E. Puckett Professor of Electrical Engineering at Caltech. He directs the Computation and Neural Systems (www.cns.caltech.edu), a PhD program centered on the study of biological brains and intelligent machines. Professor Perona’s research centers on vision. He has contributed to the theory of partial differential equations for image processing and boundary formation, and to modeling the early visual system’s function. He is currently interested in visual categories and visual recognition. Professor Pietro Perona‘s research focusses on vision: how do we see and how can we build machines that see. Professor Perona is also interested in studying how humans perform visual tasks, such as searching and recognizing image content. One of his recent projects studies how to harness the visual ability of thousands of people on the web.

PRESENTATION

PDF & VIDEO

More events

Cookie Settings

A AIDA - AI Doctoral Academy may use cookies to remember your login data, collect statistics to optimize the functionality of the site and to perform marketing actions based on your interests.


These cookies are necessary to allow the main functionality of the website and are automatically activated when you use this website.
These cookies allow us to analyze the use of the website, so that we can measure and improve its performance.
Allow you to stay in touch with your social network, share content, send and post comments.

Required Cookies They allow you to personalize the commercial offers that are presented to you, directing them to your interests. They can be own or third party cookies. We warn you that, even if you do not accept these cookies, you will receive commercial offers, but without meeting your preferences.

Functional Cookies They offer a more personalized and complete experience, allow you to save preferences, show you content relevant to your taste and send you the alerts you have requested.

Advertising Cookies Allow you to stay in touch with your social network, share content, send and post comments.