April 5, 2024, 4:45 a.m. | Tianwei Chen, Yusuke Hirota, Mayu Otani, Noa Garcia, Yuta Nakashima

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.03242v1 Announce Type: new
Abstract: 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 accompany them, potentially leading to the dissemination of harmful content. This paper explores whether a detrimental feedback loop, resulting in bias amplification, would occur if generated images were used as the training data for future models. We conduct simulations by progressively …

abstract ai-generated images amplify arxiv bias biases computer computer vision concerns cs.cv deep generative models future generated generative generative models images impact internet paper social them type vision vision models

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Senior Data Engineer

@ Quantexa | Sydney, New South Wales, Australia

Staff Analytics Engineer

@ Warner Bros. Discovery | NY New York 230 Park Avenue South