2024/05/23 by Dongjun Kim, Kim, Dongjun, Chieh-Hsin Lai +13 · 11 citations
Computer Science · #Advanced Data Compression Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Educational Technology and Assessment #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2405.14822
openalex publication_date 2024/05/23 · openalex created_date 2024/05/25 · openalex updated_date 2026/07/28
The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a 64× reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNet across all resolutions from 64x64 to 512x512, and text-to-image. PaGoDA's pipeline can be applied directly in the latent space, adding compression alongside the pre-trained autoencoder in Latent Diffusion Models (e.g., Stable Diffusion). The code is available at https://github.com/sony/pagoda.