Project AURIONAI Use-Cases Research & Innovation
University of North Carolina at Chapel Hill
visionfamily

SSD (Single Shot MultiBox Detector)

One-stage multi-box detector from Wei Liu and colleagues; with MobileNet backbones it is the standard detector on phones and microcontrollers.

University of North Carolina at Chapel HillUniversity of North Carolina at Chapel HillUSAGoogleGoogleUSA
Figure from the SSD paper: the SSD framework matching default boxes at several feature map scales.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released8 Dec 2015
Opennessunknown
Runs onmobile or NPU, CPU server
Statusactive

Lineage

201520162017201820192020SSD-ResNet34 (MLPerf)SSD-ResNet34 (MLPerf), Dec 2015SSD MobileNet v2SSD MobileNet v2, Jan 2018SSDLite, Jan 2018NVIDIA SSD300NVIDIA SSD300, Mar 2019
NVIDIANVIDIA SSD300 belongs to this familyvisionMar 2019
GoogleSSD MobileNet v2 belongs to this familyvision13 Jan 2018
GoogleSSDLite belongs to this familyvision13 Jan 2018
University of North Carolina at Chapel HillSSD-ResNet34 (MLPerf) belongs to this familyvision8 Dec 2015
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

Real-time object detection (YOLO and DETR lines)produced by

Identity

Developer
University of North Carolina at Chapel Hill, Google
Family
not in the notes
Released
8 Dec 2015 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
SSD300 and SSD512 with VGG16, ResNet-34 (MLPerf) and ResNet-50 (NVIDIA); SSD MobileNet v1 is already in AURION (ssd-mobilenet-v1).
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, CPU server
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO, TI edge AI model zoo, MediaPipe.
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/1512.02325 https://arxiv.org/abs/1512.02325
  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/resnet34_ssd1200 https://aihub.qualcomm.com/models/resnet34_ssd1200
  4. github.com/mlcommons/inference/tree/33894a19c4af6207f7cf... https://github.com/mlcommons/inference/tree/33894a19c4af6207f7cfdda75f84570f04836de5/vision/classification_and_detection
  5. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/ssd-resnet34-1200-onnx
  6. catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/ssd__pyt_ckpt https://catalog.ngc.nvidia.com/orgs/nvidia/teams/dle/models/ssd__pyt_ckpt
  7. github.com/TexasInstruments/edgeai-tensorlab/tree/main/e... https://github.com/TexasInstruments/edgeai-tensorlab/tree/main/edgeai-modelzoo/models/vision/detection/coco
  8. arxiv.org/html/1512.02325 https://arxiv.org/html/1512.02325

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SSD (Single Shot MultiBox Detector)", https://aurion.semai.id/models/ssd/, records of October 2026.