ShuffleNetV2
E431006
ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
All labels observed (2)
| Label | Occurrences |
|---|---|
| ShuffleNet architecture | 1 |
| ShuffleNetV2 canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4325999 — 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: ShuffleNetV2 Context triple: [torchvision, modelFamily, ShuffleNetV2]
-
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.
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.
-
D.
LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
-
E.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
- 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: ShuffleNetV2 Target entity description: ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
-
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.
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.
-
D.
LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
-
E.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
convolutional neural network architecture
ⓘ
deep learning model ⓘ image classification architecture ⓘ |
| comparedTo | ShuffleNet NERFINISHED ⓘ |
| designedFor |
efficient image classification
ⓘ
resource-constrained devices ⓘ |
| emphasizes |
low computational cost
ⓘ
speed ⓘ |
| evaluatedOn | ImageNet NERFINISHED ⓘ |
| hasComponent |
bottleneck blocks
ⓘ
channel split operation ⓘ feature concatenation ⓘ residual connections ⓘ |
| hasDesignGoal |
hardware-friendly architecture
ⓘ
improved practical speed on real devices ⓘ low FLOPs ⓘ reduced memory access cost ⓘ |
| hasGuideline |
element-wise operations are non-trivial in cost
ⓘ
equal channel width minimizes memory access cost ⓘ excessive group convolution increases memory access cost ⓘ network fragmentation reduces degree of parallelism ⓘ |
| hasProperty |
balanced computation across branches
ⓘ
lightweight ⓘ low latency ⓘ optimized for embedded devices ⓘ optimized for mobile devices ⓘ reduced fragmentation in computation graph ⓘ small model size ⓘ suitable for real-time inference ⓘ |
| hasVariant |
ShuffleNetV2 0.5x
NERFINISHED
ⓘ
ShuffleNetV2 1.0x NERFINISHED ⓘ ShuffleNetV2 1.5x NERFINISHED ⓘ ShuffleNetV2 2.0x NERFINISHED ⓘ |
| implementedIn |
ONNX model zoo
NERFINISHED
ⓘ
PyTorch NERFINISHED ⓘ TensorFlow NERFINISHED ⓘ |
| improvesUpon | ShuffleNet NERFINISHED ⓘ |
| introducedBy | researchers from Megvii (Face++) ⓘ |
| introducedIn | paper "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" NERFINISHED ⓘ |
| isSuccessorOf | ShuffleNet NERFINISHED ⓘ |
| outperforms | ShuffleNet on speed-accuracy tradeoff (under similar FLOPs) ⓘ |
| publicationYear | 2018 ⓘ |
| usedFor |
embedded vision applications
ⓘ
mobile vision applications ⓘ real-time image recognition ⓘ |
| uses |
channel shuffle operation
ⓘ
depthwise convolutions ⓘ pointwise convolutions ⓘ |
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: ShuffleNetV2 Description of subject: ShuffleNetV2 is a lightweight convolutional neural network architecture designed for efficient image classification on resource-constrained devices, emphasizing speed and low computational cost.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
torchvision
this entity surface form:
ShuffleNet architecture