Related papers: Does Data-Efficient Generalization Exacerbate Bias…

Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across…

Computer vision models have been known to encode harmful biases, leading to the potentially unfair treatment of historically marginalized groups, such as people of color. However, there remains a lack of datasets balanced along demographic…

In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that trained models significantly amplify the association of target…

The label bias and selection bias are acknowledged as two reasons in data that will hinder the fairness of machine-learning outcomes. The label bias occurs when the labeling decision is disturbed by sensitive features, while the selection…

Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness. Neglecting such metrics in training can make these models prone to fairness violations when…

In recent years, image and video manipulations with Deepfake have become a severe concern for security and society. Many detection models and datasets have been proposed to detect Deepfake data reliably. However, there is an increased…

Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols,…

Machine learning models are increasingly used in critical decision-making applications. However, these models are susceptible to replicating or even amplifying bias present in real-world data. While there are various bias mitigation methods…

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…

Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features. This raises the question of whether…

Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions. Researchers observe a significant performance disparity among subgroups with…

Building AI systems, including Facial Expression Recognition (FER), involves two critical aspects: data and model design. Both components significantly influence bias and fairness in FER tasks. Issues related to bias and fairness in FER…

Machine learning (ML) models often exhibit bias that can exacerbate inequities in biomedical applications. Fairness auditing, the process of evaluating a model's performance across subpopulations, is critical for identifying and mitigating…

With the growing utilization of machine learning in healthcare, there is increasing potential to enhance healthcare outcomes. However, this also brings the risk of perpetuating biases in data and model design that can harm certain…

Pre-training representations (a.k.a. foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the…

With the rapid expansion of machine learning and deep learning (DL), researchers are increasingly employing learning-based algorithms to alleviate diagnostic challenges across diverse medical tasks and applications. While advancements in…

While the need for well-trained, fair ML systems is increasing ever more, measuring fairness for modern models and datasets is becoming increasingly difficult as they grow at an unprecedented pace. One key challenge in scaling common…

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper…

Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation…

Ear disease contributes significantly to global hearing loss, with recurrent otitis media being a primary preventable cause in children, impacting development. Artificial intelligence (AI) offers promise for early diagnosis via otoscopic…