IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?
Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, XIAOJUAN QI
Abstract
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 the data-scare 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.
BibTeX
@inproceedings{
he2023is,
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},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=nUmCcZ5RKF}
}