Project AURIONAI Use-Cases Research & Innovation
University of Oregon
vision

OneFormer

One transformer trained once for semantic, instance and panoptic segmentation.

University of OregonUniversity of OregonUSAUniversity of Illinois Urbana-ChampaignUniversity of Illinois Urbana-ChampaignUSA
Diagram comparing specialised, partially unified and universal segmentation, with OneFormer as one model for all tasks, from the model card.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released10 Nov 2022
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

R&D Topics

Semantic, instance and panoptic segmentation architecturesproduced by

Identity

Developer
University of Oregon, University of Illinois Urbana-Champaign
Family
not in the notes
Released
10 Nov 2022 sourcesannouncement page
Weights published
15 Nov 2022
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
MIT License sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2211.06220 https://arxiv.org/abs/2211.06220
  2. huggingface.co/shi-labs/oneformer_ade20k_swin_large https://huggingface.co/shi-labs/oneformer_ade20k_swin_large
  3. ai.azure.com/catalog/models?task=image-segmentation https://ai.azure.com/catalog/models?task=image-segmentation
  4. huggingface.co/shi-labs/oneformer_cityscapes_swin_large https://huggingface.co/shi-labs/oneformer_cityscapes_swin_large
  5. huggingface.co/api/models?pipeline_tag=image-segmentation&so... https://huggingface.co/api/models?pipeline_tag=image-segmentation&sort=downloads&limit=50
  6. arxiv.org/html/2211.06220 https://arxiv.org/html/2211.06220

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OneFormer", https://aurion.semai.id/models/oneformer/, records of October 2026.