# Hugging Face — Universal Image Segmentation with Mask2Former and OneFormer

- Company: Hugging Face (huggingface.co)
- Announced: 2023-01-19
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/mask2former
- Record: https://forck.live/items/2110-universal-image-segmentation-with-mask2former-and-oneformer
- Subject: Platform
- Models affected: Mask2Former, OneFormer

Mask2Former and OneFormer, two state-of-the-art neural networks for image segmentation, now available in the 🤗 transformers open-source library. The models adopt a unified architecture for instance, semantic, and panoptic segmentation.

## Evidence

Verbatim from https://huggingface.co/blog/mask2former:

> This guide introduces Mask2Former and OneFormer, 2 state-of-the-art neural networks for image segmentation. The models are now available in 🤗 transformers

---

Record: https://forck.live/items/2110-universal-image-segmentation-with-mask2former-and-oneformer
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md