Project AURIONAI Use-Cases Research & Innovation
Microsoft AI
vision

Swin Transformer V2

Swin scaled to higher capacity and resolution, from the paper "Swin Transformer V2: Scaling Up Capacity and Resolution".

Microsoft AIMicrosoft AIUSASwin TransformerFamily
Figure from the Swin Transformer V2 paper: Visualization of the learnt relative position bias matrices by different approaches, using a SwinV2-T model and the 3 heads in the first block.
Levelvariant
Classvision
Parametersnot in the notes
Contextnot in the notes
Released18 Nov 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

successor
Swin-B to Swin Transformer V2: successor, high confidenceSwin-BSwin-BMicrosoft AI, Mar 2021Swin Transformer V2Swin Transformer V2Microsoft AI, Nov 2021
Microsoft AISwin-B is the parent (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Image classification backbone architectures (CNN and vision transformer)produced by

Identity

Developer
Microsoft AI
Family
Swin Transformer
Released
18 Nov 2021 sourcesannouncement page
Weights published
14 Jun 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
labels and boxes
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
Apache License 2.0 sources
Access routes
open weights download
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.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2111.09883 https://arxiv.org/abs/2111.09883
  2. huggingface.co/microsoft/swinv2-tiny-patch4-window16-256 https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Swin Transformer V2", https://aurion.semai.id/models/microsoft-swin-v2/, records of October 2026.