5 papers
Gender Artifacts from Art History to Text-to-Image Generation
Piera Riccio, Miriam Doh, Benedikt Höltgen +2
Artistic styles are rooted in specific socio-historical contexts that encode social hierarchies, including distinct constructions of gender. Yet in AI research, style has long been…
ImageSet2Text: Describing Sets of Images through Text
Piera Riccio, Francesco Galati, Kajetan Schweighofer +2
In the era of large-scale visual data, understanding collections of images is a challenging yet important task. To this end, we introduce ImageSet2Text, a novel method to automatic…
The Iconicity of the Generated Image
Nanne van Noord, Noa Garcia
How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to…
From Global to Local: Social Bias Transfer in CLIP
Ryan Ramos, Yusuke Hirota, Yuta Nakashima +1
The recycling of contrastive language-image pre-trained (CLIP) models as backbones for a large number of downstream tasks calls for a thorough analysis of their transferability imp…
Data Leakage in Visual Datasets
Patrick Ramos, Ryan Ramos, Noa Garcia
We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given th…