Project AURIONAI Use-Cases Research & Innovation
ETRI (Electronics and Telecommunications Research Institute)
vision

VoVNet

Energy and GPU-efficient backbone for real-time object detection built from one-shot aggregation modules.

ETRI (Electronics and Telecommunications Research Institute)ETRI (Electronics and Telecommunications Research Institute)South Korea
Figure from the VoVNet paper: The average absolute filter weights of convolutional layers in trained DenseNet (top) and VoVNet (middle, bottom).
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released22 Apr 2019
Opennessunknown
Runs onnot in the notes
Statusactive

R&D Topics

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

Identity

Developer
ETRI (Electronics and Telecommunications Research Institute)
Family
not in the notes
Released
22 Apr 2019 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
VoVNet v1 and v2 (v2 from the CenterMask paper, arXiv 1911.06667).
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
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/1904.09730 https://arxiv.org/abs/1904.09730
  2. github.com/youngwanLEE/vovnet-detectron2 https://github.com/youngwanLEE/vovnet-detectron2
  3. github.com/huggingface/pytorch-image-models/blob/main/RE... https://github.com/huggingface/pytorch-image-models/blob/main/README.md
  4. arxiv.org/abs/1911.06667 https://arxiv.org/abs/1911.06667
  5. github.com/onnx/models/tree/main/Computer_Vision/ese_vov... https://github.com/onnx/models/tree/main/Computer_Vision/ese_vovnet19b_dw_Opset16_timm
  6. arxiv.org/html/1904.09730 https://arxiv.org/html/1904.09730

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