Project AURIONAI Use-Cases Research & Innovation
visionfamily

ResNeXt

Residual network with grouped "cardinality" branches, from the paper "Aggregated Residual Transformations for Deep Neural Networks"; used as an ImageNet classifier and as a detection backbone in Detectron2.

UC San DiegoUC San DiegoUSAMetaMetaUSA
UC San Diego
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released16 Nov 2016
Opennessunknown
Runs onmobile or NPU
Statusactive

Lineage

MetaResNeXt-101 32x8d WSL belongs to this familyvision2 May 2018
UC San DiegoResNeXt-50 32x4d belongs to this familyvision16 Nov 201625M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

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

Identity

Developer
UC San Diego, Meta
Family
not in the notes
Released
16 Nov 2016 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
ResNeXt-50 32x4d, 101 32x8d and 152; Instagram weakly supervised (WSL) and semi-supervised (SSL, SWSL) weights.
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
unknown
Licence
not in the notes sources
Access routes
open weights download, cloud marketplace
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.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1611.05431 https://arxiv.org/abs/1611.05431
  2. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  3. aihub.qualcomm.com/models/resnext50 https://aihub.qualcomm.com/models/resnext50
  4. github.com/pytorch/vision/blob/main/torchvision/models/r... https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py
  5. catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/resnext_101-32x4... https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/resnext_101-32x4d_pyt_ckpt
  6. pytorch.org/hub/pytorch_vision_resnext https://pytorch.org/hub/pytorch_vision_resnext
  7. raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_resnext.md https://raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_resnext.md
  8. arxiv.org/html/1611.05431 https://arxiv.org/html/1611.05431

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