Domain adaptation for visual applications: A comprehensive survey
G Csurka - arXiv preprint arXiv:1702.05374, 2017 - arxiv.org
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 …
a specific view on visual applications. After a general motivation, we first position domain …
Review and analysis of synthetic dataset generation methods and techniques for application in computer vision
G Paulin, M Ivasic‐Kos - Artificial intelligence review, 2023 - Springer
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 …
become a necessity. Although they have been used in computer vision since 1989, helping …
Stablerep: Synthetic images from text-to-image models make strong visual representation learners
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 …
generated by text-to-image models. This is a natural question in the light of the excellent …
Scaling laws of synthetic images for model training... for now
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 …
systems using synthetic images potentially overcoming the difficulty of collecting curated …
Fake it till you make it: face analysis in the wild using synthetic data alone
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 …
synthetic data alone. The community has long enjoyed the benefits of synthesizing training …
[图书][B] Synthetic data for deep learning
SI Nikolenko - 2021 - Springer
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 …
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
Augmented reality meets computer vision: Efficient data generation for urban driving scenes
H Abu Alhaija, SK Mustikovela, L Mescheder… - International Journal of …, 2018 - Springer
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 …
annotated datasets. To lower the need for hand labeled images, virtually rendered 3D …
Beyond sharing weights for deep domain adaptation
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 …
degrades when applied to a related but different one. While annotating many samples from …
A vision check-up for language models
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 …
(LLMs) about the visual world? We systematically evaluate LLMs' abilities to generate and …
Deep adversarial attention alignment for unsupervised domain adaptation: the benefit of target expectation maximization
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 …
the convolutional neural network (CNN). First, our approach transfers knowledge in all the …