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 3151–3200 of 8378 papers

TitleStatusHype
Dual-Granularity Contrastive Learning for Session-based Recommendation—0
Tailoring Domain Adaptation for Machine Translation Quality EstimationCode0
TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image ModelsCode0
Stochastic Subgraph Neighborhood Pooling for Subgraph ClassificationCode0
Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose EstimationCode0
Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis—0
Synthetic Data from Diffusion Models Improves ImageNet Classification—0
JoB-VS: Joint Brain-Vessel Segmentation in TOF-MRA ImagesCode0
Meta-optimized Contrastive Learning for Sequential RecommendationCode1
Few-shot Weakly-supervised Cybersecurity Anomaly Detection—0
Icospherical Chemical Objects (ICOs) allow for chemical data augmentation and maintain rotational, translation and permutation invariance—0
FSDNet-An efficient fire detection network for complex scenarios based on YOLOv3 and DenseNet—0
Real-Time Helmet Violation Detection Using YOLOv5 and Ensemble Learning—0
1-D Residual Convolutional Neural Network coupled with Data Augmentation and Regularization for the ICPHM 2023 Data Challenge—0
Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10—0
A Byte Sequence is Worth an Image: CNN for File Fragment Classification Using Bit Shift and n-Gram EmbeddingsCode0
PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute RecognitionCode1
Real-Time Helmet Violation Detection in AI City Challenge 2023 with Genetic Algorithm-Enhanced YOLOv5—0
How Will It Drape Like? Capturing Fabric Mechanics from Depth Images—0
Understanding Overfitting in Adversarial Training via Kernel Regression—0
Assessment Framework for Deepfake Detection in Real-world Situations—0
Regularizing Contrastive Predictive Coding for Speech Applications—0
Towards Understanding How Data Augmentation Works with Imbalanced DataCode0
Few-shot Class-incremental Learning for Cross-domain Disease Classification—0
Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation—0
Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 AlgorithmCode1
An Efficient Transfer Learning-based Approach for Apple Leaf Disease Classification—0
Isolated Sign Language Recognition based on Tree Structure Skeleton ImagesCode1
Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement LearningCode0
Transfer Learning for Low-Resource Sentiment AnalysisCode0
Use the Detection Transformer as a Data AugmenterCode0
A Deep Learning Approach Towards Generating High-fidelity Diverse Synthetic Battery Datasets—0
Embarrassingly Simple MixUp for Time-series—0
Propheter: Prophetic Teacher Guided Long-Tailed Distribution LearningCode0
Attack-Augmentation Mixing-Contrastive Skeletal Representation LearningCode0
SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented DataCode0
Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle RecognitionCode1
HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular DatasetsCode1
Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting—0
Leveraging GANs for data scarcity of COVID-19: Beyond the hype—0
Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data—0
What makes a good data augmentation for few-shot unsupervised image anomaly detection?—0
Noise-Robust Dense Retrieval via Contrastive Alignment Post Training—0
Patch-aware Batch Normalization for Improving Cross-domain Robustness—0
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluationCode1
Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets—0
Benchmarking Robustness to Text-Guided CorruptionsCode0
Performance of Data Augmentation Methods for Brazilian Portuguese Text Classification—0
Adaptive Data Augmentation for Contrastive Learning—0
Learning Stage-wise GANs for Whistle Extraction in Time-Frequency SpectrogramsCode0
Show:102550
← PrevPage 64 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