Related papers: Representation Debiasing of Generated Data Involvi…

The significant advancements in applying Artificial Intelligence (AI) to healthcare decision-making, medical diagnosis, and other domains have simultaneously raised concerns about the fairness and bias of AI systems. This is particularly…

Recent advancements in image generation technology have enabled widespread access to AI-generated imagery, prominently used in advertising, entertainment, and progressively in every form of visual content. However, these technologies often…

Social bias in generative AI can manifest not only as performance disparities but also as associational bias, whereby models learn and reproduce stereotypical associations between concepts and demographic groups, even in the absence of…

Datasets are crucial when training a deep neural network. When datasets are unrepresentative, trained models are prone to bias because they are unable to generalise to real world settings. This is particularly problematic for models trained…

We investigate the impact of deep generative models on potential social biases in upcoming computer vision models. As the internet witnesses an increasing influx of AI-generated images, concerns arise regarding inherent biases that may…

AI leaders and companies have much to offer to AI/ML practitioners to support them in addressing and mitigating biases in the AI/ML systems they develop. AI/ML practitioners need to receive the necessary resources and support from experts…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

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…

Human-in-the-loop machine learning is widely used in artificial intelligence (AI) to elicit labels for data points from experts or to provide feedback on how close the predicted results are to the target. This simplifies away all the…

Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind…

A variety of interesting parameters may depend on high dimensional regressions. Machine learning can be used to estimate such parameters. However estimators based on machine learners can be severely biased by regularization and/or model…

Recommender systems rely on user behavior data like ratings and clicks to build personalization model. However, the collected data is observational rather than experimental, causing various biases in the data which significantly affect the…

Surveillance systems play a critical role in security and reconnaissance, but their performance is often compromised by low-quality images and videos, leading to reduced accuracy in face recognition. Additionally, existing AI-based facial…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

With the advent of generative modeling techniques, synthetic data and its use has penetrated across various domains from unstructured data such as image, text to structured dataset modeling healthcare outcome, risk decisioning in financial…

Due to the widespread use of data-powered systems in our everyday lives, concepts like bias and fairness gained significant attention among researchers and practitioners, in both industry and academia. Such issues typically emerge from the…

Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discrimination in AI. Despite…

Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We…

Machine learning models built on datasets containing discriminative instances attributed to various underlying factors result in biased and unfair outcomes. It's a well founded and intuitive fact that existing bias mitigation strategies…