相关论文: Gender Artifacts in Visual Datasets

Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal…

This study delves into gender classification systems, shedding light on the interaction between social stereotypes and algorithmic determinations. Drawing on the "averageness theory," which suggests a relationship between a face's…

Gender bias in Language and Vision datasets and models has the potential to perpetuate harmful stereotypes and discrimination. We analyze gender bias in two Language and Vision datasets. Consistent with prior work, we find that both…

The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time,…

Diffusion model-generated images can appear indistinguishable from authentic photographs, but these images often contain artifacts and implausibilities that reveal their AI-generated provenance. Given the challenge to public trust in media…

Movies reflect society and also hold power to transform opinions. Social biases and stereotypes present in movies can cause extensive damage due to their reach. These biases are not always found to be the need of storyline but can creep in…

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…

Large scale image classification models trained on top of popular datasets such as Imagenet have shown to have a distributional skew which leads to disparities in prediction accuracies across different subsections of population…

The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on training binary classifiers, which depend heavily on the…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls and women, which…

Facial forgery by deepfakes has raised severe societal concerns. Several solutions have been proposed by the vision community to effectively combat the misinformation on the internet via automated deepfake detection systems. Recent studies…

This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a…

The accelerated advancement of generative AI significantly enhance the viability and effectiveness of generative regional editing methods. This evolution render the image manipulation more accessible, thereby intensifying the risk of…

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…

Gender bias represents a form of systematic negative treatment that targets individuals based on their gender. This discrimination can range from subtle sexist remarks and gendered stereotypes to outright hate speech. Prior research has…

Text-to-image models, which can generate high-quality images based on textual input, have recently enabled various content-creation tools. Despite significantly affecting a wide range of downstream applications, the distributions of these…

Large pre-trained language models have become a crucial backbone for many downstream tasks in natural language processing (NLP), and while they are trained on a plethora of data containing a variety of biases, such as gender biases, it has…

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…