vision
Attention-based segmentation networks (MMSegmentation)
Group of semantic segmentation networks that add attention or context modules to a dilated ResNet; all are reproduced with checkpoints in OpenMMLab MMSegmentation.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released9 Sep 2018
Opennessunknown
Runs onnot in the notes
Statusactive
Identity
- Developer
- Institute of Automation, Chinese Academy of Sciences, JD.com
- Family
- not in the notes
- Released
- 9 Sep 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
- DANet (arXiv 1809.02983), CCNet (1811.11721), EMANet (1907.13426), ANN (1908.07678), APCNet, DMNet, DNLNet (2006.06668), EncNet (1803.08904), FastFCN (1903.11816), ISANet (1907.12273), NonLocal Net (1711.07971), PSANet.
- 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
DevelopersInstitute of Automation, Chinese Academy of Sciencesnational lab, China
JD.combig tech, China
Institute of Automation, Chinese Academy of Sciencesnational lab, ChinaJD.combig tech, ChinaModelAttention-based segmentation networks (MMSegmentation)Institute of Automation, Chinese Academy of Sciences, vision
Attention-based segmentation networks (MMSegmentation)Institute of Automation, Chinese Academy of Sciences, visionUse CasesMedical Image SegmentationHealthcareRobotic Waste and Recycling SortingIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 2
Sources
- arxiv.org/abs/1809.02983 https://arxiv.org/abs/1809.02983
- github.com/open-mmlab/mmsegmentation/tree/main/configs/d... https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dnlnet
- arxiv.org/abs/2006.06668 https://arxiv.org/abs/2006.06668
- github.com/open-mmlab/mmsegmentation/tree/main/configs/i... https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet
- arxiv.org/abs/1907.12273 https://arxiv.org/abs/1907.12273
- github.com/open-mmlab/mmsegmentation/tree/main/configs/f... https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn
- arxiv.org/abs/1903.11816 https://arxiv.org/abs/1903.11816
- arxiv.org/html/1809.02983 https://arxiv.org/html/1809.02983
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Attention-Based Segmentation Networks (MMSegmentation)", https://aurion.semai.id/models/attention-segmentation-networks/, records of October 2026.