Chameleon: Foundation models for fairness-aware multi-modal data augmentation to enhance coverage of minorities
The potential harms of the under-representation of minorities in training data, particularly in
multi-modal settings, is a well-recognized concern. While there has been extensive effort in …
multi-modal settings, is a well-recognized concern. While there has been extensive effort in …
Gender in Pixels: Pathways to Non-binary Representation in Computer Vision
E Beretta - Proceedings of the AAAI/ACM Conference on AI, Ethics …, 2024 - ojs.aaai.org
In the field of Computer Vision (CV), the study of bias, including gender bias, has received a
significant area of attention in recent years. However, these studies predominantly operate …
significant area of attention in recent years. However, these studies predominantly operate …
Coverage-based Data-centric Approaches for Responsible and Trustworthy AI.
The grand goal of data-driven decision systems is to help make decisions easier, more
accurate, at a higher scale, and also just. However, data-driven algorithms are only as good …
accurate, at a higher scale, and also just. However, data-driven algorithms are only as good …
Mining the Minoria: Unknown, Under-represented, and Under-performing Minority Groups
M Dehghankar, A Asudeh - arXiv preprint arXiv:2411.04761, 2024 - arxiv.org
Due to a variety of reasons, such as privacy, data in the wild often misses the grouping
information required for identifying minorities. On the other hand, it is known that machine …
information required for identifying minorities. On the other hand, it is known that machine …