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 4851–4900 of 8378 papers

TitleStatusHype
MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant TrainingCode1
Robust Hybrid Learning With Expert AugmentationCode1
DeepSSN: a deep convolutional neural network to assess spatial scene similarityCode0
Field-of-View IoU for Object Detection in 360° Images—0
SODA: Self-organizing data augmentation in deep neural networks -- Application to biomedical image segmentation tasks—0
Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study—0
SimGRACE: A Simple Framework for Graph Contrastive Learning without Data AugmentationCode1
Multi-modal data generation with a deep metric variational autoencoder—0
Data set creation and empirical analysis for detecting signs of depression from social media postingsCode1
LiDAR dataset distillation within bayesian active learning framework: Understanding the effect of data augmentation—0
TTS-GAN: A Transformer-based Time-Series Generative Adversarial NetworkCode2
Exemplar-Based Contrastive Self-Supervised Learning with Few-Shot Class Incremental Learning—0
Fairness for Text Classification Tasks with Identity Information Data Augmentation Methods—0
Multi-Output Gaussian Process-Based Data Augmentation for Multi-Building and Multi-Floor Indoor Localization—0
Deep invariant networks with differentiable augmentation layersCode1
The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge—0
Supervised Contrastive Learning for Product MatchingCode1
Bootstrapped Representation Learning for Skeleton-Based Action Recognition—0
A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes—0
Learning Mechanically Driven Emergent Behavior with Message Passing Neural NetworksCode0
The RoyalFlush System of Speech Recognition for M2MeT Challenge—0
NoisyMix: Boosting Model Robustness to Common Corruptions—0
Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls—0
Deep Learning in fNIRS: A review—0
Compositionality as Lexical SymmetryCode0
Improving Robustness by Enhancing Weak SubnetsCode0
Graph Representation Learning via Aggregation EnhancementCode1
FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform LossCode1
Improving End-to-End Models for Set Prediction in Spoken Language Understanding—0
You Only Cut Once: Boosting Data Augmentation with a Single CutCode1
Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation—0
Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition—0
Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency ParsingCode0
Arrhythmia Classification using CGAN-augmented ECG SignalsCode1
Tackling data scarcity in speech translation using zero-shot multilingual machine translation techniquesCode0
Recency Dropout for Recurrent Recommender Systems—0
Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images—0
Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal Transport Augmentation—0
ViT-HGR: Vision Transformer-based Hand Gesture Recognition from High Density Surface EMG SignalsCode1
Neural Manifold Clustering and EmbeddingCode1
On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems—0
Synthetic speech detection using meta-learning with prototypical loss—0
Feature transforms for image data augmentationCode0
A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification—0
VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges—0
Fair Node Representation Learning via Adaptive Data Augmentation—0
Dual Contrastive Learning: Text Classification via Label-Aware Data AugmentationCode1
Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze EstimationCode0
Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction—0
Lung Swapping Autoencoder: Learning a Disentangled Structure-texture Representation of Chest RadiographsCode0
Show:102550
← PrevPage 98 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