相关论文: Discovering and Mitigating Visual Biases through K…

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…

The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular…

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features. In contrast to prior works which utilize object…

Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…

Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with…

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…

Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released in February would struggle to generate a…

In the quest for fairness in artificial intelligence, novel approaches to enhance it in facial image based gender classification algorithms using text guided methodologies are presented. The core methodology involves leveraging semantic…

ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and…

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…

Computer vision models have been shown to exhibit and amplify biases across a wide array of datasets and tasks. Existing methods for quantifying bias in classification models primarily focus on dataset distribution and model performance on…

Image captioning has made substantial progress with huge supporting image collections sourced from the web. However, recent studies have pointed out that captioning datasets, such as COCO, contain gender bias found in web corpora. As a…

Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy. To address this issue, we present an adaptive multi-model…

Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a…

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…

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…

Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development…

Vision-language models (VLMs) have gained widespread adoption in both industry and academia. In this study, we propose a unified framework for systematically evaluating gender, race, and age biases in VLMs with respect to professions. Our…