Project AURIONAI Use-Cases Research & Innovation
Huazhong University of Science and Technology
vision

BiSeNet

Bilateral network for real-time semantic segmentation.

Figure from the BiSeNet paper: An overview of the Bilateral Segmentation Network.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released2 Aug 2018
Opennessunknown
Runs onmobile or NPU
Statusactive

R&D Topics

Identity

Developer
Huazhong University of Science and Technology, Megvii
Family
not in the notes
Released
2 Aug 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
–
Note
BiSeNet V1 and V2 (arXiv 2004.02147); Qualcomm AI Hub phone build.
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
unknown
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub.
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/1808.00897 https://arxiv.org/abs/1808.00897
  2. huggingface.co/qualcomm/BiseNet https://huggingface.co/qualcomm/BiseNet
  3. github.com/open-mmlab/mmsegmentation/tree/main/configs/b... https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2
  4. arxiv.org/abs/2004.02147 https://arxiv.org/abs/2004.02147
  5. github.com/open-mmlab/mmsegmentation/tree/main/configs/b... https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1
  6. arxiv.org/html/1808.00897 https://arxiv.org/html/1808.00897

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