Used for reproducing results of "Label-Efficient Semantic Segmentation with Diffusion Models" (ICLR 2022)

This repository contains weights and features extracted from a Denoising Diffusion Probabilistic Model (DDPM) for segmentation tasks. DDPM Weights can be found at "https://huggingface.co/Harish-JHR/DDPM_CelebAHQ64". Following the approach in the referenced paper, we extract pixel-level features from the UpBlock layers of the DDPM and train lightweight segmentation heads on them.

Each MLP corresponds to a segmentation head trained on different layers/features.