The WACV 2022 2nd Workshop on Explainable & Interpretable Artificial Intelligence for Biometrics (xAI4Biometrics Workshop 2022) intends to promote research on Explainable & Interpretable-AI to facilitate the implementation of AI/ML in the biometrics domain, and specifically to help facilitate transparency and trust.

This workshop will include two keynote talks by:

•            Walter J. Scheirer, Notre Dame University, USA

•            Speaker TBA

The xAI4Biometrics Workshop 2022 is organized by INESC TEC, Porto, Portugal and co-organized by the European Association for Biometrics (EAB).

For more information please visit http://vcmi.inesctec.pt/xai4biometrics

IMPORTANT DATES

Abstract submission (mandatory): October 04, 2021

Full Paper Submission Deadline: October 11, 2021

Acceptance Notification: November 15, 2021

Camera-ready & Registration: November 19, 2021

Conference: January 04-08, 2022 | Workshop Date: January 04, 2022

TOPICS OF INTEREST

The xAI4Biometrics welcomes works that focus on biometrics and promote the development of:

•            Methods to interpret the biometric models to validate their decisions as well as to improve the models and to detect possible vulnerabilities;

•            Quantitative methods to objectively assess and compare different explanations of the automatic decisions;

•            Methods and metrics to study/evaluate the quality of explanations obtained by post-model approaches and improve the explanations;

•            Methods to generate model-agnostic  explanations;

•            Transparency and fairness in AI algorithms avoiding bias;

•            Methods that use post-model explanations to improve the models’ training;

•            Methods to achieve/design inherently interpretable algorithms (rule-based, case-based reasoning, regularization methods);

•            Study on causal learning, causal discovery, causal reasoning, causal explanations, and causal inference;

•            Natural Language generation for explanatory models;

•            Methods for adversarial attacks detection, explanation and defense (“How can we interpret adversarial examples?”);

•            Theoretical approaches of explainability (“What makes a good explanation?”);

•            Applications of all the above including proofs-of-concept and demonstrators of how to integrate explainable AI into real-world workflows and industrial processes.

ORGANIZING COMMITTEES

GENERAL CHAIRS

o            Jaime S. Cardoso, INESC TEC and University of Porto, Portugal

o            Ana F. Sequeira, INESC TEC, Porto, Portugal

o            Arun Ross, Michigan State University, USA

o            Peter Eisert, Humboldt University & Fraunhofer HHI

o            Cynthia Rudin, Duke University, USA

PROGRAMME CHAIRS

o            Christoph Busch, NTNU & Hochschule Darmstadt

o            Tiago de Freitas Pereira, IDIAP Research Institute, Switzerland

o            Wilson Silva, INESC TEC and University of Porto, Portugal

CONTACT

Ana Filipa Sequeira, PhD (ana.f.sequeira@inesctec.pt)

Assistant Researcher

INESC TEC, Porto, Portugal

Dr.-Ing. Naser Damer

Smart Living & Biometric Technologies

Fraunhofer Institute for Computer Graphics Research IGD

Fraunhoferstr. 5  |  64283 Darmstadt  |  Germany Tel +49 6151 155-521

Fax +49 6151 155-499 | naser.damer@igd.fraunhofer.de  | www.igd.fraunhofer.de