Data Augmentation

Data augmentation involves techniques used for increasing the amount of data, based on different modifications, to expand the amount of examples in the original dataset. Data augmentation not only helps to grow the dataset but it also increases the diversity of the dataset. When training machine learning models, data augmentation acts as a regularizer and helps to avoid overfitting.

Data augmentation techniques have been found useful in domains like NLP and computer vision. In computer vision, transformations like cropping, flipping, and rotation are used. In NLP, data augmentation techniques can include swapping, deletion, random insertion, among others.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 8326–8350 of 8378 papers

Title	Date	Tasks	Status	Hype
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings	Dec 1, 2015	Data AugmentationMulti-Label Learning	—Unverified	0
Towards Dropout Training for Convolutional Neural Networks	Dec 1, 2015	Data Augmentation	—Unverified	0
On-line Recognition of Handwritten Mathematical Symbols	Nov 29, 2015	Data Augmentation	—Unverified	0
What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks	Nov 23, 2015	Data AugmentationZero-Shot Learning	—Unverified	0
A Unified Gradient Regularization Family for Adversarial Examples	Nov 19, 2015	BIG-bench Machine LearningData Augmentation	—Unverified	0
Convolutional neural networks with low-rank regularization	Nov 19, 2015	Data AugmentationTensor Decomposition	CodeCode Available	1
Reducing Overfitting in Deep Networks by Decorrelating Representations	Nov 19, 2015	Data Augmentation	—Unverified	0
Bayesian Analysis of Dynamic Linear Topic Models	Nov 12, 2015	Data AugmentationDynamic Topic Modeling	—Unverified	0
Weakly Supervised Deep Detection Networks	Nov 9, 2015	ClassificationData Augmentation	CodeCode Available	0
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation	Oct 9, 2015	Data AugmentationFeature Engineering	—Unverified	0
That's So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using \#petpeeve Tweets	Sep 1, 2015	Data Augmentation	—Unverified	0
DeepWriterID: An End-to-end Online Text-independent Writer Identification System	Aug 20, 2015	Data Augmentation	—Unverified	0
What is Holding Back Convnets for Detection?	Aug 12, 2015	Data Augmentationobject-detection	—Unverified	0
Dropout Training for SVMs with Data Augmentation	Aug 10, 2015	Data AugmentationRepresentation Learning	—Unverified	0
Multimodal Deep Learning for Robust RGB-D Object Recognition	Jul 24, 2015	Data AugmentationDeep Learning	CodeCode Available	0
Manitest: Are classifiers really invariant?	Jul 23, 2015	Data Augmentation	—Unverified	0
Towards Good Practices for Very Deep Two-Stream ConvNets	Jul 8, 2015	Action RecognitionAction Recognition In Videos	CodeCode Available	1
Soccer jersey number recognition using convolutional neural networks	Jul 1, 2015	Data AugmentationJersey Number Recognition	—Unverified	0
Dropout as data augmentation	Jun 29, 2015	Data Augmentation	—Unverified	0
Deep CNN Ensemble with Data Augmentation for Object Detection	Jun 24, 2015	Data AugmentationObject	—Unverified	0
Locally Adaptive Dynamic Networks	May 21, 2015	Data AugmentationPosition	—Unverified	0
Character-level Chinese Writer Identification using Path Signature Feature, DropStroke and Deep CNN	May 19, 2015	Data Augmentation	—Unverified	0
APAC: Augmented PAttern Classification with Neural Networks	May 13, 2015	ClassificationData Augmentation	—Unverified	0
Learning Temporal Embeddings for Complex Video Analysis	May 2, 2015	Data AugmentationRetrieval	—Unverified	0
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks	Apr 30, 2015	Data AugmentationModel Discovery	—Unverified	0

Show:10 25 50

← PrevPage 334 of 336Next →

All datasets ImageNet CIFAR-10 GA1457

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DeiT-B (+MixPro)	Accuracy (%)	82.9	—	Unverified
2	ResNet-200 (DeepAA)	Accuracy (%)	81.32	—	Unverified
3	DeiT-S (+MixPro)	Accuracy (%)	81.3	—	Unverified
4	ResNet-200 (Fast AA)	Accuracy (%)	80.6	—	Unverified
5	ResNet-200 (UA)	Accuracy (%)	80.4	—	Unverified
6	ResNet-200 (AA)	Accuracy (%)	80	—	Unverified
7	ResNet-50 (DeepAA)	Accuracy (%)	78.3	—	Unverified
8	ResNet-50 (TA wide)	Accuracy (%)	78.07	—	Unverified
9	ResNet-50 (LoRot-E)	Accuracy (%)	77.72	—	Unverified
10	ResNet-50 (LoRot-I)	Accuracy (%)	77.71	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	WideResNet-40-2 (Faster AA)	Percentage error	3.7	—	Unverified
2	Shake-Shake (26 2×32d) (Faster AA)	Percentage error	2.7	—	Unverified
3	WideResNet-28-10 (Faster AA)	Percentage error	2.6	—	Unverified
4	Shake-Shake (26 2×112d) (Faster AA)	Percentage error	2	—	Unverified
5	Shake-Shake (26 2×96d) (Faster AA)	Percentage error	2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DiffAug	Classification Accuracy	92.7	—	Unverified
2	PaCMAP	Classification Accuracy	85.3	—	Unverified
3	hNNE	Classification Accuracy	77.4	—	Unverified
4	TopoAE	Classification Accuracy	74.6	—	Unverified