This paper introduces Representation-Conditioned image Generation (RCG), a framework for high-quality image generation without human annotations. RCG achieves state-of-the-art results on ImageNet and bridges the performance gap between class-unconditional and class-conditional image generation. Code is available.

https://arxiv.org/abs//2312.03701

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers