image generation
SPGAN
Image-to-image domain adaptation GAN that translates labelled images to a new camera domain for person re-identification.
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
Released19 Nov 2017
Opennessunknown
Runs onnot in the notes
Statusactive
R&D Topics
Identity
- Developer
- University of Chinese Academy of Sciences, University of Technology Sydney
- Family
- not in the notes
- Released
- 19 Nov 2017 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
- In OpenMMLab OpenUnReID (Apache-2.0).
- 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
- 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.
Links
DevelopersUniversity of Chinese Academy of Sciencesuniversity, China
University of Technology Sydneyuniversity, Australia
University of Chinese Academy of Sciencesuniversity, ChinaUniversity of Technology Sydneyuniversity, AustraliaModelSPGANUniversity of Chinese Academy of Sciences, image generation
SPGANUniversity of Chinese Academy of Sciences, image generationR&D TopicsGenerative Image Modelling Methods (GANs, Diffusion and Image Translation)Multi-Object Tracking and Re-Identification
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 2
R&D topics 2
Generative Image Modelling Methods (GANs, Diffusion and Image Translation)Core methods for learning to generate or translate images, from GANs and autoencoders to…produced byMulti-Object Tracking and Re-IdentificationFollowing people, vehicles or animals across video frames and cameras and recognising the…produced by
Sources
- arxiv.org/abs/1711.07027 https://arxiv.org/abs/1711.07027
- github.com/open-mmlab/OpenUnReID/tree/master/tools/SPGAN https://github.com/open-mmlab/OpenUnReID/tree/master/tools/SPGAN
- arxiv.org/html/1711.07027 https://arxiv.org/html/1711.07027
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SPGAN", https://aurion.semai.id/models/spgan/, records of October 2026.