Measuring algorithmic bias in face analysis: towards an experimental approach

Visipedia: Combining People, Data and Machines to distill and share Knowledge

**Session Chairs**: prof. Alberto del Bimbo, prof. Vittorio Murino

**Speaker**:
Pietro Perona // Measuring algorithmic bias in face analysis — towards an experimental approach

Caltech – California Institute of Technology and Amazon Web Services, USA

![](https://assets.underline.io/uploads/markdown_image/1/image/460a42358c192e5b0855e016aba550a9.jpg)


**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

**Biography**: Professor Perona's research focusses on vision: how do we see and how can we build machines that see. Professor Perona is currently interested visual recognition, more specifically visual categorization. He is studying how machines can learn to recognize frogs, cars, faces and trees with minimal human supervision, and how machines can learn from human experts. His project `Visipedia' has produced two smart device apps (iNaturalist and Merlin Bird ID) that anyone can use to recognize the species of plants and animals from a photograph.In collaboration with Professors Anderson and Dickinson, Professor Perona is building vision systems and statistical techniques for measuring actions and activities in fruit flies and mice. This enables geneticists and neuroethologists to investigate the relationship between genes, brains and behavior. 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.


Keynote by Pietro Perona

keynote

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

**Session Chair:** Mathew Lease

**TALK ABSTRACT**

Visipedia is a network of people and machines designed to harvest and organize visual information and make it accessible to anyone anywhere. I will explore technical challenges arising from Visipedia and discuss their implications for computer vision, machine learning, human-machine systems and visual psychology. I will discuss the case study, an automated field guide to the birds of North America. Key contributions include a method for characterizing the multidimensional wisdom of crowdworkers and a classification pipeline combining input from humans and machines. I will conclude by discussing several open issues encompassing algorithm development to community engagement.

**SPEAKER BIOGRAPHY**

Dr. Pietro Perona is the Allen E. Puckett Professor of Electrical Engineering at Caltech. He directs 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.


Keynote talk: Pietro Perona (Amazon): Visipedia: Combining People, Data and Machines to distill and share Knowledge

The 8th AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2020) will be held October 26–28th virtually at The Netherlands Institute for Sound and Vision in Hilversum, The Netherlands.

While artificial intelligence (AI) and human-computer interaction (HCI) represent traditional mainstays of the conference, HCOMP believes strongly in fostering and promoting broad, interdisciplinary research. Our field is particularly unique in the diversity of disciplines it draws upon and contributes to, including human-centered qualitative studies and HCI design, social computing, artificial intelligence, economics, computational social science, digital humanities, policy, and ethics. We promote the exchange of advances in human computation and crowdsourcing not only among researchers, but also engineers and practitioners, to encourage dialogue across disciplines and communities of practice.

This year, we especially invite works that will generate new insights into the quality (or qualities) of human-annotated datasets, including elements such as reliability and replicability of human computation and crowdsourcing experiments, novel metrics for aggregation of results, and holistic approaches to deal with bias, fairness and interpretability.

HCOMP 2020

HCOMP believes strongly in fostering and promoting broad, interdisciplinary research. Our field is particularly unique in the diversity of disciplines it draws upon and contributes to, including human-centered qualitative studies and HCI design, social computing, artificial intelligence, economics, computational social science, digital humanities, policy, and ethics. 


Pietro Perona

2

Presentations

Measuring algorithmic bias in face analysis: towards an experimental approach

Visipedia: Combining People, Data and Machines to distill and share Knowledge