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 6451–6500 of 8378 papers

TitleStatusHype
Sequence-Level Mixed Sample Data AugmentationCode1
An Efficient and Scalable Deep Learning Approach for Road Damage DetectionCode1
Self-supervised Document Clustering Based on BERT with Data Augment—0
Bridging the Reality Gap for Pose Estimation Networks using Sensor-Based Domain Randomization—0
Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection—0
Recovering and Simulating Pedestrians in the Wild—0
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?—0
Facebook AI's WMT20 News Translation Task Submission—0
Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI—0
NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge BasesCode0
SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images—0
On Filter Generalization for Music Bandwidth Extension Using Deep Neural NetworksCode1
Low-resource expressive text-to-speech using data augmentation—0
Text Augmentation for Language Models in High Error Recognition ScenarioCode1
Unsupervised Learning of Dense Visual Representations—0
UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised AnnotationsCode0
Medical Knowledge-enriched Textual Entailment Framework—0
Towards Domain-Agnostic Contrastive Learning—0
Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character AugmentationCode0
MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization ProblemCode1
An improved helmet detection method for YOLOv3 on an unbalanced dataset—0
LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning—0
End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales—0
Investigating Societal Biases in a Poetry Composition SystemCode0
Deep Active Learning with Augmentation-based Consistency EstimationCode0
Center-wise Local Image Mixture For Contrastive Representation Learning—0
Data Augmentation via Structured Adversarial Perturbations—0
Few-Shot Object Detection in Real Life: Case Study on Auto-Harvest—0
Teaching with CommentariesCode0
Intriguing Properties of Contrastive LossesCode2
Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translation—0
Deep Multi-task Network for Delay Estimation and Echo Cancellation—0
Sound Event Detection in Domestic Environments using Dense Recurrent Neural Network—0
Learning and Evaluating Representations for Deep One-class ClassificationCode1
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection—0
Data Augmentation for End-to-end Code-switching Speech Recognition—0
Learning Regional Purity for Instance Segmentation on 3D Point CloudsCode0
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningCode1
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks—0
Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix—0
Training Wake Word Detection with Synthesized Speech Data on Confusion Words—0
VEGA: Towards an End-to-End Configurable AutoML PipelineCode1
A Two-Stage Approach to Device-Robust Acoustic Scene ClassificationCode1
Conditioned Text Generation with Transfer for Closed-Domain Dialogue SystemsCode1
What's All the FUSS About Free Universal Sound Separation Data?—0
SapAugment: Learning A Sample Adaptive Policy for Data Augmentation—0
Semi-supervised Federated Learning for Activity Recognition—0
nnU-Net for Brain Tumor SegmentationCode1
An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution—0
Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT—0
Show:102550
← PrevPage 130 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