AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

A Unified Framework for U-Net Design and Analysis

Christopher Williams, Fabian Falck, George Deligiannidis, Christopher C. Holmes, Arnaud Doucet, Saifuddin Syed

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace learned encoder with parameter-free Haar DWT encoder and move saved parameters into decoder (Multi-ResNet)Residual U-Net · Navier-Stokesr-MSE: 0.0057 -> 0.0040Improved
replace learned encoder with parameter-free Haar DWT encoder and move saved parameters into decoder (Multi-ResNet)Residual U-Net · Shallow waterr-MSE: 0.1712 -> 0.1493Improved
replace learned encoder with parameter-free Haar DWT encoder and move saved parameters into decoder (Multi-ResNet)Residual U-Net · WMH segmentationDice: 0.8069 -> 0.8346Improved
replace learned encoder with Haar DWT encoder and add saved parameters to decoder (Multi-ResNet)Residual U-Net · CIFAR10 diffusionFID: 7.86 -> 12.44Hurt
add the saved encoder parameters to the decoder in Multi-ResNet (ablation)Multi-ResNet · Navier-Stokesr-MSE: 0.0107 -> 0.0040Improved
add the saved encoder parameters to the decoder in Multi-ResNet (ablation)Multi-ResNet · Shallow waterr-MSE: 0.4899 -> 0.1493Improved
add the saved encoder parameters to the decoder in Multi-ResNet (ablation)Multi-ResNet · WMH segmentationDice: 0.8190 -> 0.8346Improved
add the saved encoder parameters to the decoder in Multi-ResNet (ablation)Multi-ResNet · CIFAR10 diffusionFID: 14.87 -> 12.44Improved
allocate saved parameters via more hidden channels (v2) instead of more residual blocks per resolution (v1) (ablation)Multi-ResNet · Navier-Stokes and Shallow waterr-MSEHurt
train with staged multi-resolution training instead of single-stage (ablation)Residual U-Net diffusion · CIFAR10FID: 7.858 -> 8.33No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy