相关论文: BioPro: On Difference-Aware Gender Fairness for Vi…

How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness…

Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may…

To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While…

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses…

Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks. Since they are optimized to capture the statistical properties of intra- and inter-modality, there remains risk to learn…

Biases in machine learning pose significant challenges, particularly when models amplify disparities that affect disadvantaged groups. Traditional bias mitigation techniques often lead to a {\itshape leveling-down effect}, whereby improving…

Automatic segmentation of knee bony anatomy is essential in orthopedics, and it has been around for several years in both pre-operative and post-operative settings. While deep learning algorithms have demonstrated exceptional performance in…

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…

Algorithmic fairness has conventionally adopted the mathematically convenient perspective of racial color-blindness (i.e., difference unaware treatment). However, we contend that in a range of important settings, group difference awareness…

Machine learning technology has become ubiquitous, but, unfortunately, often exhibits bias. As a consequence, disparate stakeholders need to interact with and make informed decisions about using machine learning models in everyday systems.…

Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which…

LLMs have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype associations between biased concepts and specific social groups. These…

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

Bias in computer vision models remains a significant challenge, often resulting in unfair, unreliable, and non-generalizable AI systems. Although research into bias mitigation has intensified, progress continues to be hindered by fragmented…

Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. In this paper, we focus on mitigating gender bias towards vision-language tasks. We identify object hallucination as the essence of gender…

Unified multimodal large language models (U-MLLMs) have demonstrated impressive performance in visual understanding and generation in an end-to-end pipeline. Compared with generation-only models (e.g., Stable Diffusion), U-MLLMs may raise…

Unsupervised anomaly detection is a critical task in many high-social-impact applications such as finance, healthcare, social media, and cybersecurity, where demographics involving age, gender, race, disease, etc, are used frequently. In…

As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as…

Unconscious biases continue to be prevalent in modern text and media, calling for algorithms that can assist writers with bias correction. For example, a female character in a story is often portrayed as passive and powerless ("She…