Related papers: Rethinking Common Assumptions to Mitigate Racial B…

Bias can be introduced to AI systems even from seemingly balanced sources, and AI facial beauty prediction is subject to ethnicity-based bias. This work sounds warnings about AI's role in shaping aesthetic norms while providing potential…

In a world increasingly reliant on artificial intelligence, it is more important than ever to consider the ethical implications of artificial intelligence on humanity. One key under-explored challenge is labeler bias, which can create…

We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and…

A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to…

Synthetic data has emerged as a promising alternative for training face recognition (FR) models, offering advantages in scalability, privacy compliance, and potential for bias mitigation. However, critical questions remain on whether both…

Numerous studies have shown that existing Face Recognition Systems (FRS), including commercial ones, often exhibit biases toward certain ethnicities due to under-represented data. In this work, we explore ethnicity alteration and skin tone…

Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias".…

Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the…

Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and effective strategy…

In recent years, the rapid development of artificial intelligence (AI) systems has raised concerns about our ability to ensure their fairness, that is, how to avoid discrimination based on protected characteristics such as gender, race, or…

Despite the progress made in deepfake detection research, recent studies have shown that biases in the training data for these detectors can result in varying levels of performance across different demographic groups, such as race and…

Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…

Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by…

Face quality assessment aims at estimating the utility of a face image for the purpose of recognition. It is a key factor to achieve high face recognition performances. Currently, the high performance of these face recognition systems come…

Previous generations of face recognition algorithms differ in accuracy for images of different races (race bias). Here, we present the possible underlying factors (data-driven and scenario modeling) and methodological considerations for…

Face image quality assessment (FIQA) attempts to improve face recognition (FR) performance by providing additional information about sample quality. Because FIQA methods attempt to estimate the utility of a sample for face recognition, it…

Recent developments in machine learning have shown that successful models do not rely only on huge amounts of data but the right kind of data. We show in this paper how this data-centric approach can be facilitated in a decentralized manner…

Biased datasets are ubiquitous and present a challenge for machine learning. For a number of categories on a dataset that are equally important but some are sparse and others are common, the learning algorithms will favor the ones with more…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these…