Project AURIONAI Use-Cases Research & Innovation
The Chinese University of Hong Kong
vision

IBN-Net

Backbone mixing instance and batch normalisation for better generalisation across domains, from the paper "Two at Once".

The Chinese University of Hong KongThe Chinese University of Hong KongChinaSenseTimeSenseTimeChina
Diagram of the original residual block next to the IBN-a and IBN-b blocks, from the IBN-Net README.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released25 Jul 2018
Opennessopen source
Runs onnot in the notes
Statusactive

R&D Topics

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

Identity

Developer
The Chinese University of Hong Kong, SenseTime
Family
not in the notes
Released
25 Jul 2018 sourcesannouncement page
Weights published
–
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
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
image
Output
not in the notes
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 source
Licence
MIT License 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.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1807.09441 https://arxiv.org/abs/1807.09441
  2. github.com/XingangPan/IBN-Net https://github.com/XingangPan/IBN-Net
  3. pytorch.org/hub/pytorch_vision_ibnnet https://pytorch.org/hub/pytorch_vision_ibnnet
  4. raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_ibnnet.md https://raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_ibnnet.md
  5. arxiv.org/html/1807.09441 https://arxiv.org/html/1807.09441

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