Related papers: Dataset Bias Mitigation in Multiple-Choice Visual …
Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The…
While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies…
Rapid improvements in the performance of machine learning models have pushed them to the forefront of data-driven decision-making. Meanwhile, the increased integration of these models into various application domains has further highlighted…
Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would…
The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emergence of these biases in Vision Transformers (ViT).…
Imbalanced data, where the positive samples represent only a small proportion compared to the negative samples, makes it challenging for classification problems to balance the false positive and false negative rates. A common approach to…
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…
Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…
Vision-language models are growing in popularity and public visibility to generate, edit, and caption images at scale; but their outputs can perpetuate and amplify societal biases learned during pre-training on uncurated image-text pairs…
There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data…
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…
Machine learning models are known to perpetuate and even amplify the biases present in the data. However, these data biases frequently do not become apparent until after the models are deployed. Our work tackles this issue and enables the…
Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…
The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…
Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…
Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs inherently reflect biases in their training data, leading to a critical challenge: when models are…
Vision-language models (VLMs) have gained widespread adoption in both industry and academia. In this study, we propose a unified framework for systematically evaluating gender, race, and age biases in VLMs with respect to professions. Our…
Given a supervised machine learning problem where the training set has been subject to a known sampling bias, how can a model be trained to fit the original dataset? We achieve this through the Bayesian inference framework by altering the…
Visual question answering (VQA) is a challenging task, which has attracted more and more attention in the field of computer vision and natural language processing. However, the current visual question answering has the problem of language…