Related papers: REVISE: A Tool for Measuring and Mitigating Bias i…

The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic…

We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas, where each image…

Bias is an inherent threat to human decision-making, including in decisions made during software development. Extensive research has demonstrated the presence of biases at various stages of the software development life-cycle. Notably, code…

Machine learning on data streams is increasingly more present in multiple domains. However, there is often data distribution shift that can lead machine learning models to make incorrect decisions. While there are automatic methods to…

We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given that large-scale datasets are often sourced from the internet,…

The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning…

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses…

Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a…

With the advent of state-of-the-art machine learning and deep learning technologies, several industries are moving towards the field. Applications of such technologies are highly diverse ranging from natural language processing to computer…

Dataset bias, where data points are skewed to certain concepts, is ubiquitous in machine learning datasets. Yet, systematically identifying these biases is challenging without costly, fine-grained attribute annotations. We present…

Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…

With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law…

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

Following the gaze of people inside videos is an important signal for understanding people and their actions. In this paper, we present an approach for following gaze across views by predicting where a particular person is looking…

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…

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…

Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution, with rare or unseen categories posing challenges to a…

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but they still face challenges in General Visual Editing, particularly in following complex instructions, preserving appearance…

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or…

Machine learning models often make predictions that bias against certain subgroups of input data. When undetected, machine learning biases can constitute significant financial and ethical implications. Semi-automated tools that involve…