We introduce SynCLR a novel approach for learning visual representations exclusively from
synthetic images without any real data. We synthesize a large dataset of image captions …

The de-facto approach to many vision tasks is to start from pretrained visual representations,
typically learned via supervised training on ImageNet. Recent methods have explored …

Pretraining general-purpose visual features has become a crucial part of tackling many
computer vision tasks. While one can learn such features on the extensively-annotated …

Pre-trained representations are becoming crucial for many NLP and perception tasks. While
representation learning in NLP has transitioned to training on raw text without human …

Many high-level skills that are required for computer vision tasks, such as parsing questions,
comparing and contrasting semantics, and writing descriptions, are also required in other …

Self-supervised representation learning targets to learn convnet-based image
representations from unlabeled data. Inspired by the success of NLP methods in this area, in …

Advanced self-supervised visual representation learning methods rely on the instance
discrimination (ID) pretext task. We point out that the ID task has an implicit semantic …

We launch EVA, a vision-centric foundation model to explore the limits of visual
representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained …

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 …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …