ResNeXt
E367297
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.
All labels observed (6)
| Label | Occurrences |
|---|---|
| ResNeXt canonical | 1 |
| ResNeXt architecture | 1 |
| ResNeXt-101 | 1 |
| ResNeXt-152 | 1 |
| ResNeXt-50 | 1 |
| ResNeXt: Aggregated Residual Transformations for Deep Neural Networks | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T3542975 — 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: ResNeXt Context triple: [ResNet, hasVariant, ResNeXt]
-
A.
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.
-
B.
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.
-
C.
AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
-
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: ResNeXt Target entity description: 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.
-
A.
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.
-
B.
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.
-
C.
AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
-
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 recognition architecture ⓘ |
| aimsTo |
improve accuracy in image recognition tasks
ⓘ
improve computational efficiency ⓘ |
| appliedIn |
feature extraction for vision tasks
ⓘ
image classification ⓘ object detection backbones ⓘ |
| basedOn | ResNet ⓘ |
| compatibleWith | GPU acceleration ⓘ |
| controlsComplexityBy | fixing total computational cost while varying cardinality ⓘ |
| evaluatedOn |
CIFAR-10
ⓘ
surface form:
CIFAR-10 dataset
CIFAR-100 ⓘ
surface form:
CIFAR-100 dataset
ImageNet ⓘ
surface form:
ImageNet dataset
|
| extends |
ResNet bottleneck block design
ⓘ
residual learning framework ⓘ |
| firstPublishedYear | 2017 ⓘ |
| hasCodeRepository | https://github.com/facebookresearch/ResNeXt ⓘ |
| hasDesignElement |
aggregated residual transformations
ⓘ
merge stage ⓘ multiple parallel transformation paths ⓘ split stage ⓘ transform stage ⓘ |
| hasHyperparameter |
cardinality
ⓘ
depth ⓘ width ⓘ |
| hasKeyIdea | cardinality as a dimension of network design ⓘ |
| hasVariant |
ResNeXt
self-linksurface differs
ⓘ
surface form:
ResNeXt-101
ResNeXt self-linksurface differs ⓘ
surface form:
ResNeXt-152
ResNeXt self-linksurface differs ⓘ
surface form:
ResNeXt-50
|
| implementedIn |
MXNet
ⓘ
PyTorch ⓘ TensorFlow ⓘ |
| influenced | later grouped-convolution architectures ⓘ |
| introducedInPaper | Aggregated Residual Transformations for Deep Neural Networks ⓘ |
| optimizationMethod | stochastic gradient descent ⓘ |
| outperforms |
ResNet
ⓘ
surface form:
ResNet on ImageNet classification
|
| paperAuthors |
Kaiming He
ⓘ
Piotr Dollár ⓘ Ross Girshick ⓘ Saining Xie ⓘ Zhuowen Tu ⓘ |
| publishedBy |
Meta AI
ⓘ
surface form:
Facebook AI Research
|
| relatedTo |
Inception architecture
ⓘ
ResNet ⓘ |
| uses |
bottleneck blocks
ⓘ
grouped convolutions ⓘ split-transform-merge strategy ⓘ |
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: ResNeXt Description of subject: 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.
Referenced by (6)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
ResNeXt architecture
this entity surface form:
ResNeXt: Aggregated Residual Transformations for Deep Neural Networks
this entity surface form:
ResNeXt-50
this entity surface form:
ResNeXt-101
this entity surface form:
ResNeXt-152