SOTAVerified

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.

Further readings:

( Image credit: Albumentations )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 7401–7450 of 8378 papers

TitleStatusHype
Music Source Separation in the Waveform Domain—0
PanDA: Panoptic Data Augmentation—0
Enhancing Out-Of-Domain Utterance Detection with Data Augmentation Based on Word Embeddings—0
DeepSmartFuzzer: Reward Guided Test Generation For Deep LearningCode0
Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation—0
Visualizing Point Cloud Classifiers by Curvature SmoothingCode0
Computational Ceramicology—0
GANkyoku: a Generative Adversarial Network for Shakuhachi MusicCode0
Improving N-gram Language Models with Pre-trained Deep Transformer—0
Improving Conditioning in Context-Aware Sequence to Sequence Models—0
Generating Diverse Translation by Manipulating Multi-Head Attention—0
On Using SpecAugment for End-to-End Speech Translation—0
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks—0
DermGAN: Synthetic Generation of Clinical Skin Images with Pathology—0
Action Recognition Using Volumetric Motion RepresentationsCode0
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means FeaturesCode0
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling—0
Faster AutoAugment: Learning Augmentation Strategies using BackpropagationCode0
Signed Input Regularization—0
Robustness to Capitalization Errors in Named Entity Recognition—0
A Smartphone-Based Skin Disease Classification Using MobileNet CNN—0
Learning from Data-Rich Problems: A Case Study on Genetic Variant Calling—0
Improving Robustness of Task Oriented Dialog Systems—0
Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo ClassificationCode0
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation—0
XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture ClassificationCode0
Towards Understanding Gender Bias in Relation ExtractionCode0
Transforming Wikipedia into Augmented Data for Query-Focused Summarization—0
Not Enough Data? Deep Learning to the Rescue!—0
Microsoft Research Asia's Systems for WMT19—0
SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic KnowledgeCode0
SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation—0
An "augmentation-free" rotation invariant classification scheme on point-cloud and its application to neuroimaging—0
Scalable Deep Generative Relational Models with High-Order Node Dependence—0
Learning from Explanations with Neural Execution TreeCode0
Enhanced Convolutional Neural Tangent Kernels—0
Training Data Augmentation for Detecting Adverse Drug Reactions in User-Generated Content—0
Data augmentation using back-translation for context-aware neural machine translation—0
KNU-HYUNDAI's NMT system for Scientific Paper and Patent Tasks onWAT 2019—0
End-to-end Speech Translation System Description of LIT for IWSLT 2019—0
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization—0
Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders—0
SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task—0
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-TranslationCode0
Benefits of Data Augmentation for NMT-based Text Normalization of User-Generated Content—0
Supervised neural machine translation based on data augmentation and improved training \& inference process—0
Character-Based Models for Adversarial Phone Extraction: Preventing Human Sex Trafficking—0
Abstract Text Summarization: A Low Resource Challenge—0
Enhanced Transformer Model for Data-to-Text Generation—0
Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data—0
Show:102550
← PrevPage 149 of 168Next →
All datasetsImageNetCIFAR-10GA1457

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9—Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32—Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3—Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6—Unverified
5ResNet-200 (UA)Accuracy (%)80.4—Unverified
6ResNet-200 (AA)Accuracy (%)80—Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3—Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07—Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72—Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71—Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7—Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7—Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6—Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified