MobileNetV2
E431005
convolutional neural network architecture
deep learning model
image classification model
lightweight neural network architecture
MobileNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, widely used in computer vision applications and available in libraries like torchvision.
All labels observed (1)
| Label | Occurrences |
|---|---|
| MobileNetV2 canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4325998 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MobileNetV2 Context triple: [torchvision, modelFamily, MobileNetV2]
-
A.
ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
-
B.
ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
-
C.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
-
D.
Neural Architecture Search
Neural Architecture Search is an automated machine learning technique that uses algorithms to design and optimize neural network architectures without extensive human intervention.
-
E.
VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MobileNetV2 Target entity description: MobileNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, widely used in computer vision applications and available in libraries like torchvision.
-
A.
ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
-
B.
ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
-
C.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
-
D.
Neural Architecture Search
Neural Architecture Search is an automated machine learning technique that uses algorithms to design and optimize neural network architectures without extensive human intervention.
-
E.
VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
- F. None of above. chosen
Statements (54)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model ⓘ image classification model ⓘ lightweight neural network architecture ⓘ |
| activationFunction | ReLU6 ⓘ |
| affiliationOfDevelopers | Google NERFINISHED ⓘ |
| availableInLibrary |
Keras Applications
NERFINISHED
ⓘ
ONNX model zoo NERFINISHED ⓘ PyTorch torchvision NERFINISHED ⓘ TensorFlow NERFINISHED ⓘ TensorFlow Lite models NERFINISHED ⓘ |
| basedOn | MobileNet NERFINISHED ⓘ |
| designedFor |
embedded systems
ⓘ
mobile devices ⓘ resource-constrained devices ⓘ |
| developedBy |
Andrew Howard
NERFINISHED
ⓘ
Andrey Zhmoginov NERFINISHED ⓘ Liang-Chieh Chen NERFINISHED ⓘ Mark Sandler NERFINISHED ⓘ Menglong Zhu NERFINISHED ⓘ |
| FLOPs | approximately 300 million multiply-adds (1.0 width, 224x224) ⓘ |
| hasDesignFeature |
ReLU6 activation
ⓘ
batch normalization ⓘ bottleneck residual blocks ⓘ depthwise separable convolutions ⓘ expansion layers ⓘ inverted residual blocks ⓘ linear bottlenecks ⓘ |
| hasLayerType |
convolutional layers
ⓘ
depthwise convolutional layers ⓘ fully connected classification layer ⓘ pointwise (1x1) convolutional layers ⓘ |
| hasPretrainedWeightsOn | ImageNet NERFINISHED ⓘ |
| licenseOfReferenceImplementation | Apache License 2.0 NERFINISHED ⓘ |
| normalization | batch normalization ⓘ |
| optimizationGoal |
computational efficiency
ⓘ
deployment on mobile devices ⓘ low memory footprint ⓘ |
| paperVenue | CVPR 2018 NERFINISHED ⓘ |
| parameterCount | approximately 3.4 million parameters (1.0 width, 224x224) ⓘ |
| precedes | MobileNetV3 NERFINISHED ⓘ |
| publicationYear | 2018 ⓘ |
| publishedIn | "MobileNetV2: Inverted Residuals and Linear Bottlenecks" NERFINISHED ⓘ |
| succeeds | MobileNetV1 NERFINISHED ⓘ |
| supports |
different number of classes
ⓘ
resolution multiplier ⓘ width multiplier ⓘ |
| typicalInput | RGB images ⓘ |
| typicalInputResolution | 224x224 ⓘ |
| usedFor |
feature extraction
ⓘ
image classification ⓘ object detection backbones ⓘ semantic segmentation backbones ⓘ transfer learning ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: MobileNetV2 Description of subject: MobileNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, widely used in computer vision applications and available in libraries like torchvision.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
torchvision