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 4176–4200 of 8378 papers

TitleStatusHype
Data-Efficient Methods for Dialogue Systems—0
Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection—0
Data Expansion Using WordNet-based Semantic Expansion and Word Disambiguation for Cyberbullying Detection—0
Data for free: Fewer-shot algorithm learning with parametricity data augmentation—0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
Data Instance Prior for Transfer Learning in GANs—0
Data InStance Prior (DISP) in Generative Adversarial Networks—0
Data Interpolating Prediction: Alternative Interpretation of Mixup—0
DataLoc+: A Data Augmentation Technique for Machine Learning in Room-Level Indoor Localization—0
Data Priming Network for Automatic Check-Out—0
Data Scarcity in Recommendation Systems: A Survey—0
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora—0
Data Techniques For Online End-to-end Speech Recognition—0
DATScore: Evaluating Translation with Data Augmented Translations—0
D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes—0
DA-VEGAN: Differentiably Augmenting VAE-GAN for microstructure reconstruction from extremely small data sets—0
DAWSON: Data Augmentation using Weak Supervision On Natural Language—0
DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition—0
DCENWCNet: A Deep CNN Ensemble Network for White Blood Cell Classification with LIME-Based Explainability—0
D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation—0
DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes—0
DE-ABUSE@TamilNLP-ACL 2022: Transliteration as Data Augmentation for Abuse Detection in Tamil—0
Dealing with the Evil Twins: Improving Random Augmentation by Addressing Catastrophic Forgetting of Diverse Augmentations—0
De-amplifying Bias from Differential Privacy in Language Model Fine-tuning—0
De-Bias for Generative Extraction in Unified NER Task—0
Show:102550
← PrevPage 168 of 336Next →
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