Learning Transferable Architectures for Scalable Image Recognition
E499148
"Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Learning Transferable Architectures for Scalable Image Recognition canonical | 4 |
How this entity was disambiguated
This entity first appeared as the object of triple T5175100 — 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: Learning Transferable Architectures for Scalable Image Recognition Context triple: [Barret Zoph, notableWork, Learning Transferable Architectures for Scalable Image Recognition]
-
A.
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.
-
B.
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.
-
C.
SqueezeNet
SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
-
D.
MobileNetV2
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.
-
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: Learning Transferable Architectures for Scalable Image Recognition Target entity description: "Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
-
A.
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.
-
B.
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.
-
C.
SqueezeNet
SqueezeNet is a compact deep convolutional neural network architecture designed to achieve AlexNet-level image classification accuracy with dramatically fewer parameters, making it efficient for deployment on resource-constrained devices.
-
D.
MobileNetV2
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.
-
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 (42)
| Predicate | Object |
|---|---|
| instanceOf |
computer vision paper
ⓘ
research paper ⓘ |
| application |
image classification benchmarks
ⓘ
transfer learning for vision tasks ⓘ |
| architectureType | convolutional neural network architecture ⓘ |
| category |
image classification literature
ⓘ
neural architecture search literature ⓘ |
| contribution |
scalable image recognition architectures
ⓘ
search on small dataset and transfer to large dataset ⓘ transferable convolutional cell architectures ⓘ |
| dataset |
CIFAR-10
ⓘ
ImageNet ⓘ |
| demonstrates |
efficient architecture transfer from CIFAR-10 to ImageNet
ⓘ
state-of-the-art accuracy on ImageNet at time of publication ⓘ |
| evaluates | accuracy versus computational cost of architectures ⓘ |
| field |
computer vision
ⓘ
deep learning ⓘ machine learning ⓘ |
| focusesOn |
automated neural network architecture design
ⓘ
large-scale image classification ⓘ |
| impact |
influenced later neural architecture search methods
ⓘ
popularized NASNet architectures ⓘ used as baseline in many NAS studies ⓘ |
| introduces |
NASNet-A
ⓘ
linked to:
NASNet
NASNet-B ⓘ
linked to:
NASNet
NASNet-C ⓘ
linked to:
NASNet
|
| introducesConcept |
normal cell in NASNet
ⓘ
reduction cell in NASNet ⓘ |
| method | neural architecture search with reinforcement learning ⓘ |
| optimizationObjective |
improve accuracy-computation trade-off on ImageNet
ⓘ
maximize validation accuracy on CIFAR-10 ⓘ |
| proposes | NASNet ⓘ |
| researchArea |
convolutional neural networks
ⓘ
image recognition ⓘ neural architecture search ⓘ |
| shortTitle | NASNet paper ⓘ |
| shows |
searched architectures outperform hand-designed architectures on ImageNet
ⓘ
searched cells can be stacked to form deep networks ⓘ |
| title | Learning Transferable Architectures for Scalable Image Recognition ⓘ |
| uses |
cell-based search space
ⓘ
controller recurrent neural network ⓘ reinforcement learning for architecture search ⓘ |
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: Learning Transferable Architectures for Scalable Image Recognition Description of subject: "Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
Learning Transferable Architectures for Scalable Image Recognition
→
title
→
Learning Transferable Architectures for Scalable Image Recognition
ⓘ