Home / AIO Classes / Preprocessing / Data Augmentation

Data Augmentation

Preprocessing AIO:DataAugmentation NOT_REVIEWED

A data enhancement used to increase the diversity and quantity of training data by applying various transformations such as rotation scaling flipping and cropping to existing data samples enhancing the robustness and performance of machine learning models.

Ontology IRI: https://w3id.org/aio/DataAugmentation

Ontology Structure & Relationships

Parent Classes

AIO:DataEnhancement (DataEnhancement)

Branches

Preprocessing

Annotations & Sources

Synonyms:

Data Enrichment exact
Data Expansion exact
Paraphrasing related
Synonym replacement related

Subsets:

https://w3id.org/aio/PreprocessingSubset

Curated AIMech Concepts Grounded to this Class

15 Concepts

Curated Concept	Kind	Mapping Relation	Rationale
AdaMixUp `AIMech:AdaMixUp`	Algorithms	related_match	This algorithm learns transformations or synthetic examples for training. The AIO target denotes augmentation in the preprocessing branch; the local procedure includes policy learning and model training, so the association is related rather than equivalent or an asserted subclass.
AutoAugment `AIMech:AutoAugment`	Algorithms	related_match	This algorithm selects or learns transformations used for augmented training examples. The AIO target denotes data augmentation in the preprocessing branch, while the local identity includes a selection or training procedure; no equivalence or subclass membership is asserted.
Bayesian Data Augmentation for Deep Models `AIMech:BayesianDataAugmentation`	Algorithms	related_match	The method generates additional labeled training samples. AIO’s augmentation node describes transformation-based data enhancement within preprocessing, whereas this method jointly learns generation and classification during training; a related mapping preserves that distinction.
CTAugment `AIMech:CTAugment`	Algorithms	related_match	This algorithm selects or learns transformations used for augmented training examples. The AIO target denotes data augmentation in the preprocessing branch, while the local identity includes a selection or training procedure; no equivalence or subclass membership is asserted.
CutMix `AIMech:CutMix`	Algorithms	related_match	This procedure constructs training examples and specifies how a predictor is trained with them. The AIO target is augmentation in a preprocessing branch; this related association preserves the broader training and target-handling scope without asserting equivalence or a subclass relation.
Cutout `AIMech:Cutout`	Preprocessing Methods	broad_match	Cutout is one particular transformation of training images that creates masked examples. The pinned AIO class denotes the broader data-augmentation method category; the relation is local-to-broader-target and does not edit the ontology.
Fast AutoAugment `AIMech:FastAutoAugment`	Algorithms	related_match	This algorithm learns transformations or synthetic examples for training. The AIO target denotes augmentation in the preprocessing branch; the local procedure includes policy learning and model training, so the association is related rather than equivalent or an asserted subclass.
Manifold Mixup `AIMech:ManifoldMixup`	Algorithms	related_match	The procedure creates synthetic representation-target pairs during end-to-end training. This is related to the preprocessing augmentation class but is not merely an input preprocessing transform.
MixUp `AIMech:MixUp`	Algorithms	related_match	The procedure constructs virtual training pairs by interpolating existing examples. The AIO target is data augmentation in a preprocessing branch, whereas this local record also specifies target interpolation and predictor training; this is a related association, not equivalence or a subclass claim.
Population Based Augmentation `AIMech:PopulationBasedAugmentation`	Algorithms	related_match	This algorithm learns transformations or synthetic examples for training. The AIO target denotes augmentation in the preprocessing branch; the local procedure includes policy learning and model training, so the association is related rather than equivalent or an asserted subclass.
RandAugment `AIMech:RandAugment`	Algorithms	related_match	This algorithm selects or learns transformations used for augmented training examples. The AIO target denotes data augmentation in the preprocessing branch, while the local identity includes a selection or training procedure; no equivalence or subclass membership is asserted.
SMOTE-NC `AIMech:SMOTENC`	Preprocessing Methods	broad_match	SMOTE-NC constructs additional mixed-feature training examples from observed minority examples through continuous interpolation and nominal-neighbor voting. The pinned data-augmentation concept is broader than this particular preprocessing method. This is a local-to-broader mapping, not equivalence, an upstream ontology edit, a neural preprocessing layer or a guarantee of improved robustness or predictive accuracy.
SamplePairing `AIMech:SamplePairing`	Algorithms	related_match	This procedure constructs training examples and specifies how a predictor is trained with them. The AIO target is augmentation in a preprocessing branch; this related association preserves the broader training and target-handling scope without asserting equivalence or a subclass relation.
Smart Augmentation `AIMech:SmartAugmentation`	Algorithms	related_match	This procedure constructs training examples and specifies how a predictor is trained with them. The AIO target is augmentation in a preprocessing branch; this related association preserves the broader training and target-handling scope without asserting equivalence or a subclass relation.
Synthetic Minority Over-sampling Technique `AIMech:SyntheticMinorityOversamplingTechnique`	Preprocessing Methods	broad_match	SMOTE constructs additional minority-class training vectors by transforming existing examples through within-class interpolation. The pinned augmentation class is broader than this particular continuous-feature synthesis procedure; this is a local-to-broader mapping, not identity or an upstream ontology edit.

Import Provenance & Upstream Synchronization

Source Repo: AIO GitHub

Release Version: aio.json

Commit: 397851c547…

License: CC-BY-4.0

Imported At: 2026-10-10T07:34:10Z

SHA256: 8f741d71408c…

Source File: data/aio/DataAugmentation.yaml