Browse by author
Lookup NU author(s): Dr Xinhuan ShuORCiD
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 1995-2012 IEEE.Bias in machine learning datasets occurs when certain attributes are unfairly associated, e.g., serious males being mostly linked with law enforcement officers in job-related image datasets. Training models on biased datasets will degrade model performance and lead to fairness issues, particularly for underrepresented groups. Existing bias detection methods mainly focus on male explicit biases associated with predefined attributes (e.g., gender and ethnicity) while overlooking implicit biases associated with subtler, dataset-specific attributes (e.g., facial expressions and attire). To address this gap, we present BiasField, an interactive tool that offers a closed-loop workflow for detecting, analyzing, and mitigating bias. Central to BiasField is the adaptive detection of both explicit and implicit biases, a process facilitated by the automatic extraction of the dataset-specific attributes. It then employs a plant-growth metaphor to visualize these biases, enabling structured analysis to identify similar biases and track how they strengthen with additional attributes. Finally, confirmed biases are mitigated through targeted generative data augmentation. A user study, two case studies, and an expert study are conducted to demonstrate its capability to detect, analyze, and mitigate complex biases.
Author(s): Li Z, Yang W, Shu X, Zhu J, Zhang H, Liu S
Publication type: Article
Publication status: Published
Journal: IEEE Transactions on Visualization and Computer Graphics
Year: 2026
Pages: epub ahead of print
Online publication date: 25/05/2026
Acceptance date: 02/04/2018
ISSN (print): 1077-2626
ISSN (electronic): 1941-0506
Publisher: IEEE Computer Society
URL: https://doi.org/10.1109/TVCG.2026.3694439
DOI: 10.1109/TVCG.2026.3694439
Altmetrics provided by Altmetric
