English

Dream the Impossible: Outlier Imagination with Diffusion Models

Machine Learning 2023-09-26 v1 Computer Vision and Pattern Recognition

Abstract

Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photo-realistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework DREAM-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the in-distribution (ID) data and classes. Specifically, DREAM-OOD learns a text-conditioned latent space based on ID data, and then samples outliers in the low-likelihood region via the latent, which can be decoded into images by the diffusion model. Different from prior works, DREAM-OOD enables visualizing and understanding the imagined outliers, directly in the pixel space. We conduct comprehensive quantitative and qualitative studies to understand the efficacy of DREAM-OOD, and show that training with the samples generated by DREAM-OOD can benefit OOD detection performance. Code is publicly available at https://github.com/deeplearning-wisc/dream-ood.

Keywords

Cite

@article{arxiv.2309.13415,
  title  = {Dream the Impossible: Outlier Imagination with Diffusion Models},
  author = {Xuefeng Du and Yiyou Sun and Xiaojin Zhu and Yixuan Li},
  journal= {arXiv preprint arXiv:2309.13415},
  year   = {2023}
}

Comments

NeurIPS 2023

R2 v1 2026-06-28T12:30:28.555Z