Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis
Abstract
An emerging area of research aims to learn deep generative models with limited training data. Implicit Maximum Likelihood Estimation (IMLE), a recent technique, successfully addresses the mode collapse issue of GANs and has been adapted to the few-shot setting, achieving state-of-the-art performance. However, current IMLE-based approaches encounter challenges due to inadequate correspondence between the latent codes selected for training and those drawn during inference. This results in suboptimal test-time performance. We theoretically show a way to address this issue and propose RS-IMLE, a novel approach that changes the prior distribution used for training. This leads to substantially higher quality image generation compared to existing GAN and IMLE-based methods, as validated by comprehensive experiments conducted on nine few-shot image datasets.
Cite
Text
Vashist et al. "Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72664-4_25Markdown
[Vashist et al. "Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/vashist2024eccv-rejection/) doi:10.1007/978-3-031-72664-4_25BibTeX
@inproceedings{vashist2024eccv-rejection,
title = {{Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis}},
author = {Vashist, Chirag and Peng, Shichong and Li, Ke},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72664-4_25},
url = {https://mlanthology.org/eccv/2024/vashist2024eccv-rejection/}
}