MindSet: A Bias-Detection Interface Using a Visual Human-in-the-Loop Workflow


METADATA ONLY
Loading...

Date

2024

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Handling data artifacts is a critical and unsolved challenge in deep learning. Disregarding such asymmetries may lead to biased and socially unfair predictions, prohibiting applications in high-stake scenarios. In the case of visual data, its inherently unstructured nature makes automated bias detection especially difficult. Thus, a promising remedy is to rely on human feedback. Hu et al. [14] introduced a three-stage theoretical study framework to use a human-in-the-loop approach for bias detection in visual datasets and ran a small-sample study. While showing encouraging results, no implementation is available to enable researchers and practitioners to study their image datasets. In this work, we present a dataset-agnostic implementation based on a highly flexible web app interface. With this implementation, we aim to bring this theoretical framework into practice by following a user-centric approach. We also extend the framework so that the workflow can be adjusted to the researcher's needs in terms of the granularity of detected anomalies.

Publication status

published

Book title

Artificial Intelligence. ECAI 2023 International Workshops

Volume

1948

Pages / Article No.

93 - 105

Publisher

Springer

Event

26th European Conference on Artificial Intelligence (ECAI 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

User Interfaces; Dataset Bias; Bias in Machine Learning

Organisational unit

09822 - El-Assady, Mennatallah / El-Assady, Mennatallah check_circle

Notes

Funding

Related publications and datasets