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 …

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In
contrast, synthetic data can be freely available using a generative model (eg, DALL-E …

Recent text-to-image generation models have shown promising results in generating high-
fidelity photo-realistic images. Though the results are astonishing to human eyes, how …

Data augmentation is one of the most prevalent tools in deep learning, underpinning many
recent advances, including those from classification, generative models, and representation …

In this work, we investigate the problem of Model-Agnostic Zero-Shot Classification (MA-
ZSC), which refers to training non-specific classification architectures (downstream models) …

Generative models are now capable of producing highly realistic images that look nearly
indistinguishable from the data on which they are trained. This raises the question: if we …

Generative data augmentation, which scales datasets by obtaining fake labeled examples
from a trained conditional generative model, boosts classification performance in various …

Abstract We propose GAN-Supervised Learning, a framework for learning discriminative
models and their GAN-generated training data jointly end-to-end. We apply our framework to …

The collection and curation of high-quality training data is crucial for developing text
classification models with superior performance, but it is often associated with significant …

Current vision systems are trained on huge datasets, and these datasets come with costs:
curation is expensive, they inherit human biases, and there are concerns over privacy and …