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 5101–5150 of 8378 papers

TitleStatusHype
Wavesplit: End-to-End Speech Separation by Speaker Clustering—0
Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding—0
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training—0
Weakly supervised training of deep convolutional neural networks for overhead pedestrian localization in depth fields—0
Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks—0
WeatherFormer: Empowering Global Numerical Weather Forecasting with Space-Time Transformer—0
WeldMon: A Cost-effective Ultrasonic Welding Machine Condition Monitoring System—0
WeMix: How to Better Utilize Data Augmentation—0
WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularization—0
WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses—0
What Affects Learned Equivariance in Deep Image Recognition Models?—0
What are effective labels for augmented data? Improving robustness with AutoLabel—0
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel—0
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study—0
What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?—0
What Do You Need for Diverse Trajectory Stitching in Diffusion Planning?—0
What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks—0
What is Holding Back Convnets for Detection?—0
What makes a good data augmentation for few-shot unsupervised image anomaly detection?—0
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different—0
What Makes for Good Views for Contrastive Learning?—0
What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?—0
What Matters for Active Texture Recognition With Vision-Based Tactile Sensors—0
What's All the FUSS About Free Universal Sound Separation Data?—0
When and How Mixup Improves Calibration—0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation—0
When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It—0
Does Data Augmentation Improve Generalization in NLP?—0
When Does Re-initialization Work?—0
When is Multi-task Learning Beneficial for Low-Resource Noisy Code-switched User-generated Algerian Texts?—0
WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation—0
Where is the bottleneck in long-tailed classification?—0
Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image—0
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods—0
Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models—0
Whisper Finetuning on Nepali Language—0
Whisper Turns Stronger: Augmenting Wav2Vec 2.0 for Superior ASR in Low-Resource Languages—0
White-box Testing of NLP models with Mask Neuron Coverage—0
White Light Specular Reflection Data Augmentation for Deep Learning Polyp Detection—0
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates—0
Who Is Your Right Mixup Partner in Positive and Unlabeled Learning—0
Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks—0
Why does music source separation benefit from cacophony?—0
Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection—0
WideResNet with Joint Representation Learning and Data Augmentation for Cover Song Identification—0
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts—0
Winning Amazon KDD Cup'24—0
Wireless Channel Aware Data Augmentation Methods for Deep Learning-Based Indoor Localization—0
Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021—0
WMD at SemEval-2020 Tasks 7 and 11: Assessing Humor and Propaganda Using Unsupervised Data Augmentation—0
Show:102550
← PrevPage 103 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