Related papers: When Cars Have Stereotypes: Auditing Demographic B…

Text-to-Image (T2I) models have transformed visual content creation, producing highly realistic images from natural language prompts. However, concerns persist around their potential to replicate and magnify existing societal biases. To…

Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their…

Generative adversarial networks conditioned on textual image descriptions are capable of generating realistic-looking images. However, current methods still struggle to generate images based on complex image captions from a heterogeneous…

This work presents a novel strategy to measure bias in text-to-image models. Using paired prompts that specify gender and vaguely reference an object (e.g. "a man/woman holding an item") we can examine whether certain objects are associated…

Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are…

Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those…

Text-to-image generative AI models such as Stable Diffusion are used daily by millions worldwide. However, the extent to which these models exhibit racial and gender stereotypes is not yet fully understood. Here, we document significant…

Images generated by text-to-image (T2I) models often exhibit visual biases and stereotypes of concepts such as culture and profession. Existing quantitative measures of stereotypes are based on statistical parity that does not align with…

This paper addresses the often overlooked issue of fairness in the autonomous driving domain, particularly in vision-based perception and prediction systems, which play a pivotal role in the overall functioning of Autonomous Vehicles (AVs).…

The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but manually annotated datasets, such as MSCOCO, are affected by…

Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a…

With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the…

Text-to-Image (TTI) generative models have shown great progress in the past few years in terms of their ability to generate complex and high-quality imagery. At the same time, these models have been shown to suffer from harmful biases,…

Text-to-Image (TTI) models are powerful creative tools but risk amplifying harmful social biases. We frame representational societal bias assessment as an image curation and evaluation task and introduce a pilot benchmark of occupational…

State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such…

Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes to this growing body of research by introducing an…

Demographic bias in text-to-image (T2I) generation is well studied, yet demographic-conditioned failures in instruction-guided image-to-image (I2I) editing remain underexplored. We examine whether identical edit instructions yield…

To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide…