The aim of this paper is to give an overview of domain adaptation and transfer learning with
a specific view on visual applications. After a general motivation, we first position domain …

Synthetic datasets, for which we propose the term synthsets, are not a novelty but have
become a necessity. Although they have been used in computer vision since 1989, helping …

We investigate the potential of learning visual representations using synthetic images
generated by text-to-image models. This is a natural question in the light of the excellent …

Recent significant advances in text-to-image models unlock the possibility of training vision
systems using synthetic images potentially overcoming the difficulty of collecting curated …

We demonstrate that it is possible to perform face-related computer vision in the wild using
synthetic data alone. The community has long enjoyed the benefits of synthesizing training …

You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …

The success of deep learning in computer vision is based on the availability of large
annotated datasets. To lower the need for hand labeled images, virtually rendered 3D …

The performance of a classifier trained on data coming from a specific domain typically
degrades when applied to a related but different one. While annotating many samples from …

What does learning to model relationships between strings teach Large Language Models
(LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and …

In this paper, we make two contributions to unsupervised domain adaptation (UDA) using
the convolutional neural network (CNN). First, our approach transfers knowledge in all the …