yandex-research/ddpm-segmentation

Label-Efficient Semantic Segmentation with Diffusion Models (ICLR'2022)

44
/ 100
Emerging

This project helps anyone working with image datasets to efficiently categorize or 'segment' objects within images. You input a small number of hand-labeled images, and it outputs a model that can automatically apply detailed pixel-level labels to new, unseen images. This is ideal for researchers, analysts, or engineers who need to precisely delineate objects in visuals, such as identifying specific facial features or distinguishing between types of furniture in a room.

715 stars. No commits in the last 6 months.

Use this if you need to perform detailed object segmentation on images but have very few examples of manually labeled data available.

Not ideal if you already have a large, richly annotated dataset for your segmentation task, or if your computational resources are limited as it can be very memory intensive.

image-analysis computer-vision visual-content-analysis dataset-labeling data-minimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

715

Forks

65

Language

Python

License

MIT

Last pushed

Apr 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/ddpm-segmentation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.