Why Are Conditional Generative Models Better Than Unconditional Ones?

Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu

Keywords: score-based model, diffusion model, self-supervised, self-conditioned

TL;DR: Analyze why conditional models outperform unconditional ones, and improve generative models in unlabelled settings.

Abstract: Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this paper, we analyze the phenomenon formally and identify that the key of conditional learning is to partition the data properly. Inspired by the analyses, we propose self-conditioned diffusion models (SCDM), which is trained conditioned on indices clustered by the $k$-means algorithm on the features extracted by a model pre-trained in a self-supervised manner. SCDM significantly improves the unconditional model across various datasets and achieves a record-breaking FID of 3.94 on ImageNet 64x64 without labels. Besides, SCDM achieves a slightly better FID than the corresponding conditional model on CIFAR10.

Student Paper: Yes

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/why-are-conditional-generative-models-better/code)