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 5701–5750 of 8378 papers

TitleStatusHype
Supervised Contrastive Learning for Accented Speech Recognition—0
Cooperative Training and Latent Space Data Augmentation for Robust Medical Image SegmentationCode1
Comparison of end-to-end neural network architectures and data augmentation methods for automatic infant motility assessment using wearable sensors—0
The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021—0
Knowledge Distillation for Quality EstimationCode0
Explainable Diabetic Retinopathy Detection and Retinal Image GenerationCode1
Zero-pronoun Data Augmentation for Japanese-to-English Translation—0
FedMix: Approximation of Mixup under Mean Augmented Federated LearningCode1
Lossless Coding of Point Cloud Geometry using a Deep Generative ModelCode1
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data AugmentationCode1
Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniquesCode0
IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task—0
Context-Aware Attention-Based Data Augmentation for POI Recommendation—0
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL—0
Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space—0
Deep Inertial Navigation using Continuous Domain Adaptation and Optimal Transport—0
Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation—0
Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment AnalysisCode1
On Improving an Already Competitive Segmentation Algorithm for the Cell Tracking Challenge - Lessons Learned—0
Are conditional GANs explicitly conditional?—0
Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning—0
Data augmentation for deep learning based accelerated MRI reconstruction with limited dataCode1
Scalable Teacher Forcing Network for Semi-Supervised Large Scale Data Streams—0
Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge GraphsCode0
Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers—0
Partially fake it till you make it: mixing real and fake thermal images for improved object detection—0
A Picture May Be Worth a Hundred Words for Visual Question Answering—0
CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals—0
Countering Adversarial Examples: Combining Input Transformation and Noisy Training—0
Decomposed Mutual Information Estimation for Contrastive Representation Learning—0
SITTA: Single Image Texture Translation for Data AugmentationCode1
Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image—0
On the (Un-)Avoidability of Adversarial Examples—0
Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-MixersCode1
ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and DissertationsCode0
Recurrent Coupled Topic Modeling over Sequential Documents—0
From Canonical Correlation Analysis to Self-supervised Graph Neural NetworksCode1
Recognising Biomedical Names: Challenges and Solutions—0
Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation—0
Data Augmentation for Opcode Sequence Based Malware Detection—0
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification—0
Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection—0
Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation—0
Customizing Graph Neural Networks using Path ReweightingCode0
Obstacle Detection for BVLOS Drones—0
Polyconvex anisotropic hyperelasticity with neural networksCode1
Learning a Facial Expression Embedding Disentangled From Identity—0
LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object Detection—0
Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image DenoisingCode1
StyleMix: Separating Content and Style for Enhanced Data AugmentationCode1
Show:102550
← PrevPage 115 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 2×96d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified