Related papers: Biased Heritage: How Datasets Shape Models in Faci…

Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and…

Fairness in deep learning models trained with high-dimensional inputs and subjective labels remains a complex and understudied area. Facial emotion recognition, a domain where datasets are often racially imbalanced, can lead to models that…

In the rapidly advancing field of artificial intelligence, machine perception is becoming paramount to achieving increased performance. Image classification systems are becoming increasingly integral to various applications, ranging from…

In recent years, Facial Expression Recognition (FER) has gained increasing attention. Most current work focuses on supervised learning, which requires a large amount of labeled and diverse images, while FER suffers from the scarcity of…

In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is an increased…

Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the…

Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model…

Facial Expression Recognition faces two core challenges. The first is class imbalance in public datasets, which skews the learning process and weakens generalization. The second is related to privacy and data collection constraints, which…

Artificial Intelligence (AI) models are now being utilized in all facets of our lives such as healthcare, education and employment. Since they are used in numerous sensitive environments and make decisions that can be life altering,…

In recent years, machine learning algorithms have become ubiquitous in a multitude of high-stakes decision-making applications. The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to…

We present a theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning. We establish novel bounds that account for distribution heterogeneity across demographic groups,…

To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…

Fairness,the impartial treatment towards individuals or groups regardless of their inherent or acquired characteristics [20], is a critical challenge for the successful implementation of Artificial Intelligence (AI) in multiple fields like…

Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real…

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…

Reliable facial expression learning (FEL) involves the effective learning of distinctive facial expression characteristics for more reliable, unbiased and accurate predictions in real-life settings. However, current systems struggle with…

We reveal critical insights into problems of bias in state-of-the-art facial recognition (FR) systems using a novel Balanced Faces In the Wild (BFW) dataset: data balanced for gender and ethnic groups. We show variations in the optimal…

Machine learning models are extensively being used to make decisions that have a significant impact on human life. These models are trained over historical data that may contain information about sensitive attributes such as race, sex,…

Recent progress in generative AI, especially diffusion models, has demonstrated significant utility in text-to-image synthesis. Particularly in healthcare, these models offer immense potential in generating synthetic datasets and training…

Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discrimination in AI. Despite…