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 7551–7600 of 8378 papers

TitleStatusHype
Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation—0
Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization—0
GraphCrop: Subgraph Cropping for Graph Classification—0
Graph data augmentation with Gromow-Wasserstein Barycenters—0
Graph Masked Autoencoder for Spatio-Temporal Graph Learning—0
Graph Mixup with Soft Alignments—0
Graph Out-of-Distribution Generalization with Controllable Data Augmentation—0
Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs—0
Graph-Regularized Manifold-Aware Conditional Wasserstein GAN for Brain Functional Connectivity Generation—0
GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification—0
Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization—0
Graph Structure Based Data Augmentation Method—0
Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation—0
Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation—0
GridMix: Strong regularization through local context mapping—0
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers—0
Grouping-By-ID: Guarding Against Adversarial Domain Shifts—0
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning—0
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks—0
GUESS: Generative Uncertainty Ensemble for Self Supervision—0
Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity Recognition—0
Guidance for Intra-cardiac Echocardiography Manipulation to Maintain Continuous Therapy Device Tip Visibility—0
Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning—0
Guided Diffusion-based Counterfactual Augmentation for Robust Session-based Recommendation—0
Guided Discrete Diffusion for Electronic Health Record Generation—0
Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation—0
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification—0
HABD: a houma alliance book ancient handwritten character recognition database—0
Hallucinations in Neural Machine Translation—0
Hallucinations in neural machine translation—0
HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI—0
HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models—0
Hand gesture recognition using 802.11ad mmWave sensor in the mobile device—0
Handling Climate Change Using Counterfactuals: Using Counterfactuals in Data Augmentation to Predict Crop Growth in an Uncertain Climate Future—0
Handling missing data in model-based clustering—0
Handling Rare Word Problem using Synthetic Training Data for Sinhala and Tamil Neural Machine Translation—0
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images—0
Handwritten Amharic Character Recognition Using a Convolutional Neural Network—0
Handwritten Digit Recognition: An Ensemble-Based Approach for Superior Performance—0
Handwritten image augmentation—0
Handwritten text generation and strikethrough characters augmentation—0
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation—0
HARD: Hard Augmentations for Robust Distillation—0
Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM—0
Hardwiring ViT Patch Selectivity into CNNs using Patch Mixing—0
Harnessing Hard Mixed Samples with Decoupled Regularizer—0
Harnessing The Power of Attention For Patch-Based Biomedical Image Classification—0
HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator—0
HARPT: A Corpus for Analyzing Consumers' Trust and Privacy Concerns in Mobile Health Apps—0
HaT5: Hate Language Identification using Text-to-Text Transfer Transformer—0
Show:102550
← PrevPage 152 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