Unsupervised Compositional Concepts Discovery with Text-to-Image
  Generative Models

Nan Liu; Yilun Du; Shuang Li; Joshua B. Tenenbaum; Antonio Torralba

返回文献探索

Paper · arXiv 2306.05357

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

Nan Liu, Yilun Du, Shuang Li, Joshua B. Tenenbaum, Antonio Torralba

3 upvotesJune 8, 2023arXiv 预印本

AI 摘要

An unsupervised method discovers generative concepts from images, enabling the creation of new images and use as a representation for classification tasks.

text-to-image generative modelshigh-resolution image synthesisunsupervised approachgenerative conceptsdisentanglingart stylesobjectslightingkitchen scenesimage classesImageNetimage representationclassification tasks

Abstract

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of different images, can we discover the generative concepts that represent each image? We present an unsupervised approach to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images. We show how such generative concepts can accurately represent the content of images, be recombined and composed to generate new artistic and hybrid images, and be further used as a representation for downstream classification tasks.