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 3701–3750 of 8378 papers

TitleStatusHype
Local Magnification for Data and Feature Augmentation—0
CST5: Data Augmentation for Code-Switched Semantic ParsingCode1
Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems—0
Hand gesture recognition using 802.11ad mmWave sensor in the mobile device—0
Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns—0
The Potential of Neural Speech Synthesis-based Data Augmentation for Personalized Speech Enhancement—0
A deep learning framework to generate realistic population and mobility data—0
Robustifying Deep Vision Models Through Shape Sensitization—0
Boosting Semi-Supervised 3D Object Detection with Semi-SamplingCode0
Adversarial and Random Transformations for Robust Domain Adaptation and Generalization—0
Textual Data Augmentation for Patient Outcomes Prediction—0
Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement—0
Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections—0
MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge DistillationCode1
Masked Contrastive Representation Learning—0
Equivariant Contrastive Learning for Sequential RecommendationCode0
MixUp-MIL: Novel Data Augmentation for Multiple Instance Learning and a Study on Thyroid Cancer DiagnosisCode0
Scalable Modular Synthetic Data Generation for Advancing Aerial Autonomy—0
Impact of Adversarial Training on Robustness and Generalizability of Language Models—0
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question AnsweringCode1
Training self-supervised peptide sequence models on artificially chopped proteins—0
Soft Augmentation for Image ClassificationCode1
Extending Temporal Data Augmentation for Video Action Recognition—0
Combination of multiple neural networks using transfer learning and extensive geometric data augmentation for assessing cellularity scores in histopathology images—0
Cold Start Streaming Learning for Deep Networks—0
IRNet: Iterative Refinement Network for Noisy Partial Label LearningCode1
A Comparative Study of Data Augmentation Techniques for Deep Learning Based Emotion Recognition—0
GOOD-D: On Unsupervised Graph Out-Of-Distribution DetectionCode1
Pushing the limits of self-supervised speaker verification using regularized distillation framework—0
Understanding the Role of Mixup in Knowledge Distillation: An Empirical StudyCode0
Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence EmbeddingCode0
Using Deep Mixture-of-Experts to Detect Word Meaning Shift for TempoWiC—0
Contrastive Weighted Learning for Near-Infrared Gaze Estimation—0
Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data—0
Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP BlockCode1
Unleashing the Power of Graph Data Augmentation on Covariate Distribution ShiftCode1
From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction—0
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations—0
Transformers on Multilingual Clause-Level MorphologyCode0
Using U-Net Network for Efficient Brain Tumor Segmentation in MRI Images—0
Evaluating a Synthetic Image Dataset Generated with Stable Diffusion—0
Conditional Generative Models for Simulation of EMG During Naturalistic MovementsCode1
Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition—0
Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided ApproachCode0
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations—0
SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation—0
Style Augmentation improves Medical Image Segmentation—0
Spatial Reasoning for Few-Shot Object Detection—0
Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds—0
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency DomainCode1
Show:102550
← PrevPage 75 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