Project AURIONAI Use-Cases Research & Innovation
Google
visionfamily

DeepLab

Google semantic segmentation family using atrous convolution and spatial pyramid pooling; DeepLabV3 with MobileNet runs on phones and microcontrollers.

GoogleGoogleUSA
Figure from the DeepLab paper: Parallel modules with atrous convolution (ASPP), augmented with image-level features.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released22 Dec 2014
Opennessunknown
Runs onmobile or NPU, CPU server, microcontroller
Statusactive

Lineage

201720182019DeepLabV3DeepLabV3, Jun 2017DeepLabV3+DeepLabV3+, Feb 2018

1 member has no release date in the notes, so it is not on this timeline.

GoogleDeepLabV3+ belongs to this familyvision7 Feb 2018
GoogleDeepLabV3 belongs to this familyvision17 Jun 2017
GoogleAutoSeg-EdgeTPU belongs to this familyvision
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

Semantic, instance and panoptic segmentation architecturesproduced by

Identity

Developer
Google
Family
not in the notes
Released
22 Dec 2014 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
DeepLabV3, DeepLabV3+ (Xception, MobileNet, ResNet backbones), DeepLab-EdgeTPU and mobile 257x257 builds.
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
mobile or NPU, CPU server, microcontroller
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO, Apple Core ML, STM32 model zoo, NXP eIQ model zoo, 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/1706.05587 https://arxiv.org/abs/1706.05587
  2. aihub.qualcomm.com/models/deeplab_xception https://aihub.qualcomm.com/models/deeplab_xception
  3. github.com/LikeLy-Journey/SegmenTron https://github.com/LikeLy-Journey/SegmenTron
  4. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/deeplabv3
  5. developer.apple.com/machine-learning/models https://developer.apple.com/machine-learning/models/
  6. github.com/STMicroelectronics/stm32ai-modelzoo/tree/main... https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/semantic_segmentation/deeplabv3
  7. github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/sema... https://github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/semantic-segmentation
  8. arxiv.org/abs/1412.7062 https://arxiv.org/abs/1412.7062

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