Related papers: Multimodal Political Bias Identification and Neutr…

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those…

Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an…

Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for…

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle…

The proliferation of machine learning models in critical decision making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many…

The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and…

It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons…

While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment. In this paper, we present a method to provide detailed textual and visual explanation of…

Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such…

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a…

Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing…

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

Extending CLIP models to semantic segmentation remains challenging due to the misalignment between their image-level pre-training objectives and the pixel-level visual understanding required for dense prediction. While prior efforts have…

Large vision-language models (VLMs) can jointly interpret images and text, but they are also prone to absorbing and reproducing harmful social stereotypes when visual cues such as age, gender, race, clothing, or occupation are present. To…

Bias mitigation in image classification has been widely researched, and existing methods have yielded notable results. However, most of these methods implicitly assume that a given image contains only one type of known or unknown bias,…

Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods,…

Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text…

The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large…