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 3601–3650 of 8378 papers

TitleStatusHype
Towards Scale Balanced 6-DoF Grasp Detection in Cluttered ScenesCode1
Graph-Regularized Manifold-Aware Conditional Wasserstein GAN for Brain Functional Connectivity Generation—0
Dynamic Test-Time Augmentation via Differentiable FunctionsCode0
Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation—0
Leveraging Contextual Data Augmentation for Generalizable Melanoma Detection—0
Visual Detection of Personal Protective Equipment and Safety Gear on Industry Workers—0
Water Bottle Defect Detection System Using Convolutional Neural Network—0
The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies—0
Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks—0
Localized Contrastive Learning on Graphs—0
Physics-guided Data Augmentation for Learning the Solution Operator of Linear Differential Equations—0
MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation—0
An Empirical Study on Multi-Domain Robust Semantic Segmentation—0
GAMMA: Generative Augmentation for Attentive Marine Debris Detection—0
GraphLearner: Graph Node Clustering with Fully Learnable AugmentationCode0
UI Layers Group Detector: Grouping UI Layers via Text Fusion and Box Attention—0
M3ST: Mix at Three Levels for Speech Translation—0
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionCode1
Region-Conditioned Orthogonal 3D U-Net for Weather4Cast CompetitionCode0
Addressing Distribution Shift at Test Time in Pre-trained Language Models—0
Tackling Low-Resourced Sign Language Translation: UPC at WMT-SLT 22Code0
ObjectStitch: Generative Object CompositingCode1
Generative Data Augmentation for Non-IID Problem in Decentralized Clinical Machine Learning—0
Towards Practical Few-shot Federated NLP—0
When Neural Networks Fail to Generalize? A Model Sensitivity PerspectiveCode0
Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric LearningCode0
Scalable and adaptive variational Bayes methods for Hawkes processes—0
CL4CTR: A Contrastive Learning Framework for CTR PredictionCode1
Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation—0
RGB no more: Minimally-decoded JPEG Vision TransformersCode1
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification—0
LUMix: Improving Mixup by Better Modelling Label UncertaintyCode0
Discrete Control in Real-World Driving Environments using Deep Reinforcement Learning—0
PatchMix Augmentation to Identify Causal Features in Few-shot Learning—0
Improving Commonsense in Vision-Language Models via Knowledge Graph RiddlesCode1
Exoplanet Detection by Machine Learning with Data Augmentation—0
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition—0
Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation—0
An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochlea—0
Semi-supervised binary classification with latent distance learning—0
Mutual Exclusivity Training and Primitive Augmentation to Induce CompositionalityCode0
Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image SegmentationCode1
DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited DataCode0
Combining Data Generation and Active Learning for Low-Resource Question AnsweringCode0
Towards Improved Input Masking for Convolutional Neural NetworksCode0
Domain generalization in fetal brain MRI segmentation \ multi-reconstruction augmentation—0
Towards Good Practices for Missing Modality Robust Action RecognitionCode1
Target-centered Subject Transfer Framework for EEG Data Augmentation—0
German Phoneme Recognition with Text-to-Phoneme Data Augmentation—0
Pose-disentangled Contrastive Learning for Self-supervised Facial RepresentationCode1
Show:102550
← PrevPage 73 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