Related papers: Markedness in Visual Semantic AI
Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and racial bias, giving…
Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored: when a model forgets a demographic group, does it…
Images can be described in terms of the objects they contain, or in terms of the types of scene or place that they instantiate. In this paper we address to what extent pretrained Vision and Language models can learn to align descriptions of…
Vision language models (VLMs), such as CLIP and OpenCLIP, can encode and reflect stereotypical associations between medical professions and demographic attributes learned from web-scale data. We present an evaluation protocol for healthcare…
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…
Humans increasingly delegate decisions to language models, yet whether these systems reproduce or reshape human patterns of discrimination remains unclear. Here we run a large-scale study to analyse whether language models use demographic…
Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…
This paper provides a comprehensive evaluation of demographic and linguistic biases in omnimodal language models that process text, images, audio, and video within a single framework. Although these models are being widely deployed, their…
The Vision-Language Pre-training (VLP) models like CLIP have gained popularity in recent years. However, many works found that the social biases hidden in CLIP easily manifest in downstream tasks, especially in image retrieval, which can…
Stereotypes, bias, and discrimination have been extensively documented in Machine Learning (ML) methods such as Computer Vision (CV) [18, 80], Natural Language Processing (NLP) [6], or both, in the case of large image and caption models…
Scale the model, scale the data, scale the GPU farms is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts on model performance remain…
Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…
Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models…
Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…
Computer vision often treats human perception as homogeneous: an implicit assumption that visual stimuli are perceived similarly by everyone. This assumption is reflected in the way researchers collect datasets and train vision models. By…
Visual perceptual tasks aim to predict human judgment of images (e.g., emotions invoked by images, image quality assessment). Unlike objective tasks such as object/scene recognition, perceptual tasks rely on subjective human assessments,…
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between…
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in…
Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…
Standard fairness audits of foundation models quantify that a model is biased, but not where inside the network the bias resides. We propose a mechanistic fairness audit that combines projected residual-stream decomposition, zero-shot…