Related papers: Discovering and Mitigating Visual Biases through K…

A person downloading a pre-trained model from the web should be aware of its biases. Existing approaches for bias identification rely on datasets containing labels for the task of interest, something that a non-expert may not have access…

Bias in generative Text-to-Image (T2I) models is a known issue, yet systematically analyzing such models' outputs to uncover it remains challenging. We introduce the Visual Bias Explorer (ViBEx) to interactively explore the output space of…

Recent progress in Text-to-Image (T2I) generative models has enabled high-quality image generation. As performance and accessibility increase, these models are gaining significant attraction and popularity: ensuring their fairness and…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

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…

Mitigating biases in computer vision models is an essential step towards the trustworthiness of artificial intelligence models. Existing bias mitigation methods focus on a small set of predefined biases, limiting their applicability in…

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 (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

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…

Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas. Existing T2I model bias evaluation methods only focus on social biases. We look…

The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become…

Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks…

Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to…

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity…

The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word…

Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…