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 applicable these generated images are for recognition tasks remains under-explored. In this work, we extensively study whether and how synthetic images generated from state-of-the-art text-to-image generation models can be used for image recognition tasks, and focus on two perspectives: synthetic data for improving classification models in data-scarce settings (i.e. zero-shot and few-shot), and synthetic data for large-scale model pre-training for transfer learning. We showcase the powerfulness and shortcomings of synthetic data from existing generative models, and propose strategies for better applying synthetic data for recognition tasks. Code: https://github.com/CVMI-Lab/SyntheticData.
@article{arxiv.2210.07574,
title = {Is synthetic data from generative models ready for image recognition?},
author = {Ruifei He and Shuyang Sun and Xin Yu and Chuhui Xue and Wenqing Zhang and Philip Torr and Song Bai and Xiaojuan Qi},
journal= {arXiv preprint arXiv:2210.07574},
year = {2023}
}