miniImageNet

E899067

few-shot learning benchmark image dataset meta-learning benchmark

miniImageNet is a widely used few-shot learning benchmark dataset derived from ImageNet, consisting of small, labeled images across many classes for evaluating meta-learning and one-shot learning algorithms.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (3)

Label	Occurrences
miniImageNet canonical	2
miniImageNet dataset	1
the need for a character-level ImageNet for one-shot learning	1

How this entity was disambiguated

This entity first appeared as the object of triple T11003621 — 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: miniImageNet
Context triple: [Matching Networks for One Shot Learning, datasetUsed, miniImageNet]

A. CIFAR-10
CIFAR-10 is a widely used computer vision dataset of 60,000 labeled low-resolution images across 10 object classes, commonly employed to benchmark image classification algorithms.
B. CIFAR-100
CIFAR-100 is a widely used image classification dataset consisting of 60,000 32×32 color images across 100 object categories, commonly used to benchmark machine learning models.
C. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
D. Matching Networks for One Shot Learning
"Matching Networks for One Shot Learning" is a seminal deep learning paper that introduced a metric-based approach for one-shot image classification using attention and memory-augmented neural networks.
E. MNIST
MNIST is a widely used benchmark dataset of handwritten digit images commonly employed for training and evaluating image classification algorithms in machine learning and computer vision.
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: miniImageNet
Target entity description: miniImageNet is a widely used few-shot learning benchmark dataset derived from ImageNet, consisting of small, labeled images across many classes for evaluating meta-learning and one-shot learning algorithms.

A. CIFAR-10
CIFAR-10 is a widely used computer vision dataset of 60,000 labeled low-resolution images across 10 object classes, commonly employed to benchmark image classification algorithms.
B. CIFAR-100
CIFAR-100 is a widely used image classification dataset consisting of 60,000 32×32 color images across 100 object categories, commonly used to benchmark machine learning models.
C. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
D. Matching Networks for One Shot Learning
"Matching Networks for One Shot Learning" is a seminal deep learning paper that introduced a metric-based approach for one-shot image classification using attention and memory-augmented neural networks.
E. MNIST
MNIST is a widely used benchmark dataset of handwritten digit images commonly employed for training and evaluating image classification algorithms in machine learning and computer vision.
F. None of above. chosen

Statements (46)

Predicate	Object
instanceOf	few-shot learning benchmark ⓘ image dataset ⓘ meta-learning benchmark ⓘ
accessMethod	constructed from ImageNet image IDs ⓘ
benchmarkRole	standard baseline for few-shot learning ⓘ
commonlyUsedWithShotCounts	1-shot ⓘ 5-shot ⓘ
commonlyUsedWithWayCounts	20-way ⓘ 5-way ⓘ
comparedWith	CIFAR-FS ⓘ linked to: CIFAR-100 FC100 ⓘ tieredImageNet ⓘ
dataFormat	image files with class labels ⓘ
derivedFrom	ImageNet ⓘ
evaluationProtocol	episodic training and testing ⓘ
hasBenchmarkProperty	fixed train/validation/test class splits ⓘ supports reproducible few-shot experiments ⓘ
hasClassBalance	approximately balanced across classes ⓘ
hasClassCount	100 ⓘ
hasDataType	natural images ⓘ
hasDomain	general object recognition ⓘ
hasFewShotSetting	N-way K-shot classification ⓘ
hasGranularity	object category level ⓘ
hasInputShape	3x84x84 (channels-first) in many implementations ⓘ
hasLabelType	image class labels ⓘ
hasLicenseSource	ImageNet license ⓘ
hasModality	RGB images ⓘ
hasNumberOfClasses	100 ⓘ
hasTask	image classification ⓘ
hasTestSplitClassCount	20 ⓘ
hasTotalImageCountApprox	60000 ⓘ
hasTrainSplitClassCount	64 ⓘ
hasTypicalImageResolution	84x84 pixels ⓘ
hasTypicalTrainImagesPerClass	600 ⓘ
hasValidationSplitClassCount	16 ⓘ
introducedFor	benchmarking meta-learning algorithms ⓘ
isSubsetOf	ImageNet ILSVRC-2012 dataset ⓘ linked to: ImageNet
isWidelyUsedSince	around 2016 ⓘ
popularizedBy	Matching Networks for One Shot Learning ⓘ Model-Agnostic Meta-Learning (MAML) ⓘ linked to: model-agnostic meta-learning Prototypical Networks for Few-shot Learning ⓘ linked to: Prototypical Networks
usedFor	few-shot learning evaluation ⓘ meta-learning evaluation ⓘ one-shot learning evaluation ⓘ
usedIn	computer vision research ⓘ machine learning research ⓘ

How these facts were elicited

Referenced by (4)

Full triples — surface form annotated when it differs from this entity's canonical label.

Matching Networks for One Shot Learning → datasetUsed → miniImageNet ⓘ

Matching Networks → appliedTo → miniImageNet dataset ⓘ

subject linked to: matching networks

linked to: miniImageNet

Relation Networks for few-shot learning → evaluatedOn → miniImageNet ⓘ

Omniglot → inspiredBy → the need for a character-level ImageNet for one-shot learning ⓘ