相关论文: Visual Identification of Problematic Bias in Large…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount…

Fine-tuning modern computer vision models requires accurately labeled data for which the ground truth may not exist, but a set of multiple labels can be obtained from labelers of variable accuracy. We tie the notion of label quality to…

Fairness constitutes a concern within machine learning (ML) applications. Currently, there is no study on how disparities in classification complexity between privileged and unprivileged groups could influence the fairness of solutions,…

There is a growing trend of applying machine learning methods to medical datasets in order to predict patients' future status. Although some of these methods achieve high performance, challenges still exist in comparing and evaluating…

Fairness in machine learning (ML) has a critical importance for building trustworthy machine learning system as artificial intelligence (AI) systems increasingly impact various aspects of society, including healthcare decisions and legal…

Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world systems. This paper presents an example of one team's…

Performance disparities of image recognition across demographic groups are known to exist in deep learning-based models, due to imbalanced group representations or spurious correlation between group and target labels. Previous work has…

Machine Learning has been applied to pathology images in research and clinical practice with promising outcomes. However, standard ML models often lack the rigorous evaluation required for clinical decisions. Machine learning techniques for…

With the growth of data sizes, visualizing them becomes more complex. Desktop displays are insufficient for presenting and collaborating on complex data visualizations. Large displays could provide the necessary space to demo or present…

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can…

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions of bias, means of quantification, and oftentimes vague…

Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although…

There has been increasing awareness of ethical issues in machine learning, and fairness has become an important research topic. Most fairness efforts in computer vision have been focused on human sensing applications and preventing…

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In…

Decision making algorithms, in practice, are often trained on data that exhibits a variety of biases. Decision-makers often aim to take decisions based on some ground-truth target that is assumed or expected to be unbiased, i.e., equally…

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…

Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient…

The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging downstream tasks such as open-vocabulary object detection and…

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for…