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
Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems—0
Topological Regularization for Graph Neural Networks Augmentation—0
MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networks—0
Neural Network Robustness as a Verification Property: A Principled Case StudyCode0
Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy—0
Data Augmentation with Manifold Barycenters—0
On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study—0
Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural NetworkCode0
Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty CalibrationCode0
A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist—0
GABO: Graph Augmentations with Bi-level Optimization—0
Sarcasm and Sentiment Detection In Arabic Tweets Using BERT-based Models and Data Augmentation—0
A Contextual Word Embedding for Arabic Sarcasm Detection with Random Forests—0
An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation—0
Few-shot learning through contextual data augmentationCode0
SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification—0
Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial TrainingCode0
Improving robustness against common corruptions with frequency biased models—0
Large Scale Autonomous Driving Scenarios Clustering with Self-supervised Feature Extraction—0
Unsupervised Disentanglement of Linear-Encoded Facial Semantics—0
Data augmentation for dealing with low sampling rates in NILM—0
Contextual Scene Augmentation and Synthesis via GSACNet—0
Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment AnalysisCode0
Learning Domain Invariant Representations for Generalizable Person Re-Identification—0
Improved Meta-Learning Training for Speaker Verification—0
Representation Learning by Ranking under multiple tasks—0
Noise Injection-based Regularization for Point Cloud Processing—0
Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data—0
Unsupervised Document Embedding via Contrastive Augmentation—0
Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers—0
An Approach to Improve Robustness of NLP Systems against ASR Errors—0
Adversarial Imitation Learning with Trajectorial Augmentation and CorrectionCode0
FakeMix Augmentation Improves Transparent Object DetectionCode0
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations—0
Efficient sign language recognition system and dataset creation method based on deep learning and image processing—0
Adversarially Optimized Mixup for Robust Classification—0
Implementation of CNN based COVID-19 classification model from CT imagesCode0
ModulOM: Disseminating Deep Learning Research with Modular Output MathematicsCode0
Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning—0
Stride and Translation Invariance in CNNs—0
Reweighting Augmented Samples by Minimizing the Maximal Expected LossCode0
Semi-supervised learning by selective training with pseudo labels via confidence estimation—0
Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving—0
XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition—0
Principled Ultrasound Data Augmentation for Classification of Standard Planes—0
Robust 2D/3D Vehicle Parsing in CVIS—0
Intraclass clustering: an implicit learning ability that regularizes DNNsCode0
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks—0
Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance—0
Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks—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