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 7151–7200 of 8378 papers

TitleStatusHype
Watching the World Go By: Representation Learning from Unlabeled VideosCode1
Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View ImagesCode1
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
OpenGAN: Open Set Generative Adversarial NetworksCode1
Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation—0
Synthesis of Brain Tumor MR Images for Learning Data AugmentationCode1
Cost-Sensitive BERT for Generalisable Sentence Classification with Imbalanced DataCode1
Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solitary Pulmonary Nodules' malignancy rating—0
Revisit Systematic Generalization via Meaningful LearningCode0
Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionCode1
End-to-end Recurrent Denoising Autoencoder Embeddings for Speaker Identification—0
On the effectiveness of convolutional autoencoders on image-based personalized recommender systems—0
Stateful Premise Selection by Recurrent Neural Networks—0
A Fourier Domain Feature Approach for Human Activity Recognition & Fall Detection—0
SuperMix: Supervising the Mixing Data AugmentationCode1
TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningCode2
Improved Baselines with Momentum Contrastive LearningCode1
DADA: Differentiable Automatic Data AugmentationCode1
Adversarial Vertex Mixup: Toward Better Adversarially Robust GeneralizationCode1
Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective—0
State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesisCode1
Evaluating Low-Resource Machine Translation between Chinese and Vietnamese with Back-Translation—0
Data Augmentation using Pre-trained Transformer ModelsCode1
DeepSperm: A robust and real-time bull sperm-cell detection in densely populated semen videos—0
XGPT: Cross-modal Generative Pre-Training for Image Captioning—0
Hybrid Deep Learning for Detecting Lung Diseases from X-ray Images—0
Do CNNs Encode Data Augmentations?—0
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation—0
Infrared and 3D skeleton feature fusion for RGB-D action recognitionCode1
A U-Net Based Discriminator for Generative Adversarial NetworksCode1
Time Series Data Augmentation for Deep Learning: A Survey—0
FMix: Enhancing Mixed Sample Data AugmentationCode1
Unshuffling Data for Improved Generalization—0
SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech TranslationCode0
Imbalance Learning for Variable Star ClassificationCode0
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
Overfitting in adversarially robust deep learningCode1
On Feature Normalization and Data AugmentationCode1
LeafGAN: An Effective Data Augmentation Method for Practical Plant Disease DiagnosisCode1
Data Augmentation for Personal Knowledge Base Population—0
A Multi-view Perspective of Self-supervised Learning—0
Data Augmentation for Copy-Mechanism in Dialogue State Tracking—0
Training Question Answering Models From Synthetic Data—0
Stochasticity in Neural ODEs: An Empirical StudyCode1
Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation—0
RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks—0
Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation—0
Wavesplit: End-to-End Speech Separation by Speaker Clustering—0
Affinity and Diversity: Quantifying Mechanisms of Data Augmentation—0
Deep Multi-Facial Patches Aggregation Network For Facial Expression Recognition—0
Show:102550
← PrevPage 144 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