ViG-Bias: Visually Grounded Bias Discovery and Mitigation
Badr-Eddine Marani, Mohamed Hanini, Nihitha Malayarukil, Stergios, Christodoulidis, Maria Vakalopoulou, Enzo Ferrante

TL;DR
ViG-Bias enhances bias discovery and mitigation in visual recognition systems by integrating visual explanations with existing methods, leading to improved performance across multiple datasets.
Contribution
The paper introduces ViG-Bias, a novel approach that incorporates visual explanations into bias detection frameworks, improving their effectiveness in identifying and mitigating biases.
Findings
Visual explanations boost bias discovery performance.
ViG-Bias improves existing methods like DOMINO, FACTS, Bias-to-Text.
Enhanced bias mitigation across diverse datasets.
Abstract
The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many occasions they are associated with hidden spurious correlations which are not easy to spot. Standard approaches rely on bias audits performed by analyzing model performance in pre-defined subgroups of data samples, usually characterized by common attributes like gender or ethnicity when it comes to people, or other specific attributes defining semantically coherent groups of images. However, it is not always possible to know a-priori the specific attributes defining the failure modes of visual recognition systems. Recent approaches propose to discover these groups by leveraging large vision language models, which enable the extraction of cross-modal…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Explainable Artificial Intelligence (XAI) · Data Visualization and Analytics
