Recent image generation models such as Stable Diffusion have exhibited an impressive
ability to generate fairly realistic images starting from a simple text prompt. Could such …

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these …

Recently, pure transformer-based models have shown great potentials for vision tasks such
as image classification and detection. However, the design of transformer networks is …

Deep learning's recent history has been one of achievement: from triumphing over humans
in the game of Go to world-leading performance in image classification, voice recognition …

This paper presents SimCLR: a simple framework for contrastive learning of visual
representations. We simplify recently proposed contrastive self-supervised learning …

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on
standard datasets can be efficiently adapted to downstream tasks. Typically, better pre …

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 …

Abstract Deep Convolutional Neural Networks have made an incredible progress in many
Computer Vision tasks. This progress, however, often relies on the availability of large …

Self-supervised visual representation learning has seen huge progress recently, but no
large scale evaluation has compared the many models now available. We evaluate the …

Abstract Convolutional Neural Networks (ConvNets) are commonly developed at a fixed
resource budget, and then scaled up for better accuracy if more resources are given. In this …