Learned representation-guided diffusion models for large-image generation

arXiv:2312.07330v2 Announce Type: replace
Abstract: To synthesize high-fidelity samples, diffusion models typically require auxiliary data to guide the generation process. However, it is impractical to procure the painstaking patch-level annotation effort required in specialized domains like histopathology and satellite imagery; it is often performed by domain experts and involves hundreds of millions of patches. Modern-day self-supervised learning (SSL) representations encode rich semantic and visual information. In this paper, we posit that such representations are expressive enough to act as proxies …

abstract annotation arxiv cs.cv data diffusion diffusion models domain domain experts domains experts fidelity guide however image image generation process representation samples satellite type