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 5001–5050 of 8378 papers

TitleStatusHype
PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition—0
Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-trainingCode0
Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation—0
Stereoscopic Universal Perturbations across Different Architectures and DatasetsCode1
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering ModelsCode0
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses—0
On Automatic Data Augmentation for 3D Point Cloud ClassificationCode0
Learning Contraction Policies from Offline Data—0
Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT—0
Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verification—0
Learning to Learn Transferable AttackCode0
Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks—0
Image-to-Image Translation-based Data Augmentation for Robust EV Charging Inlet DetectionCode0
PixMix: Dreamlike Pictures Comprehensively Improve Safety MeasuresCode1
GAN-Supervised Dense Visual AlignmentCode2
3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection—0
Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization—0
SIRfyN: Single Image Relighting from your Neighbors—0
Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy DetectionCode1
InvGAN: Invertible GANs—0
A systematic approach to random data augmentation on graph neural networks—0
Physics guided deep learning generative models for crystal materials discovery—0
Generative Adversarial Networks for Labeled Acceleration Data Augmentation for Structural Damage Detection—0
ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints—0
Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual LearningCode1
SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation—0
4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding—0
NL-Augmenter: A Framework for Task-Sensitive Natural Language AugmentationCode1
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization—0
Training Structured Neural Networks Through Manifold Identification and Variance ReductionCode0
A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems—0
RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather—0
Neural Photometry-guided Visual Attribute Transfer—0
Extracting knowledge from features with multilevel abstraction—0
Hierarchical Neural Data Synthesis for Semantic Parsing—0
Adaptive Feature Interpolation for Low-Shot Image GenerationCode1
Learning to Detect Every Thing in an Open World—0
Deep Learning-Based Carotid Artery Vessel Wall Segmentation in Black-Blood MRI Using Anatomical Priors—0
The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge—0
Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis—0
EduMT: Developing Machine Translation System for Educational Content in Indian Languages—0
Inducing Causal Structure for Interpretable Neural NetworksCode1
Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines—0
A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?—0
Object-Aware Cropping for Self-Supervised LearningCode1
Automatic Data Augmentation for Generalization in Reinforcement LearningCode1
Directed Graph Contrastive LearningCode1
Explanation-based Data Augmentation for Image ClassificationCode0
A Continuous Mapping For Augmentation Design—0
Adaptive Data Augmentation on Temporal Graphs—0
Show:102550
← PrevPage 101 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