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 3501–3525 of 8378 papers

TitleStatusHype
FusionNet: Enhanced Beam Prediction for mmWave Communications Using Sub-6GHz Channel and A Few Pilots—0
Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study—0
Anomaly Detection Using Computer Vision: A Comparative Analysis of Class Distinction and Performance Metrics—0
FUSSL: Fuzzy Uncertain Self Supervised Learning—0
A Comprehensive Augmentation Framework for Anomaly Detection—0
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning—0
Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes—0
GABO: Graph Augmentations with Bi-level Optimization—0
GADT: Enhancing Transferable Adversarial Attacks through Gradient-guided Adversarial Data Transformation—0
Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes—0
Contrastive Representation Learning for Acoustic Parameter Estimation—0
Gait Data Augmentation using Physics-Based Biomechanical Simulation—0
Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension—0
GaitMorph: Transforming Gait by Optimally Transporting Discrete Codes—0
Contrastive Self-supervised Learning for Graph Classification—0
GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation—0
Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications—0
GAMMA: Generative Augmentation for Attentive Marine Debris Detection—0
GAN-based Data Augmentation for Chest X-ray Classification—0
GAN based Data Augmentation to Resolve Class Imbalance—0
FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy—0
GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification—0
Anomaly Detection in Power Generation Plants with Generative Adversarial Networks—0
Contrastive Weighted Learning for Near-Infrared Gaze Estimation—0
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers—0
Show:102550
← PrevPage 141 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