相关论文: Evaluating Demographic Misrepresentation in Image-…

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for…

Deep learning-based person identification and verification systems have remarkably improved in terms of accuracy in recent years; however, such systems, including widely popular cloud-based solutions, have been found to exhibit significant…

The text-to-image (T2I) personalization diffusion model can generate images of the novel concept based on the user input text caption. However, existing T2I personalized methods either require test-time fine-tuning or fail to generate…

Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their…

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a…

While prior research on text-to-image generation has predominantly focused on biases in human depictions, we investigate a more subtle yet pervasive phenomenon: demographic bias in generated objects (e.g., cars). We introduce SODA…

The surge in the popularity of text-to-image generators (T2Is) has been matched by extensive research into ensuring fairness and equitable outcomes, with a focus on how they impact society. However, such work has typically focused on…

Despite advances in generation quality, current text-to-image (T2I) models often lack diversity, generating homogeneous outputs. This work introduces a framework to address the need for robust diversity evaluation in T2I models. Our…

Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for…

Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face…

Recent studies have shown that Text-to-Image (T2I) model generations can reflect social stereotypes present in the real world. However, existing approaches for evaluating stereotypes have a noticeable lack of coverage of global identity…

Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual correction and bias mitigation. Despite this common practice,…

As machine learning-enabled Text-to-Image (TTI) systems are becoming increasingly prevalent and seeing growing adoption as commercial services, characterizing the social biases they exhibit is a necessary first step to lowering their risk…

Most studies to date that have examined demographic variations in face recognition accuracy have analyzed 1-to-1 matching accuracy, using images that could be described as "government ID quality". This paper analyzes the accuracy of…

State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such…

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially…

Regional defaults describe the emerging phenomenon that text-to-image (T2I) foundation models used in generative AI are prone to over-proportionally depicting certain geographic regions to the exclusion of others. In this work, we introduce…

Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for…

Evidence shows that text-to-image (T2I) models disproportionately reflect Western cultural norms, amplifying misrepresentation and harms to minority groups. However, evaluating cultural sensitivity is inherently complex due to its fluid and…

Face recognition and verification are two computer vision tasks whose performance has progressed with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive character of face data…