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 3301–3350 of 8378 papers

TitleStatusHype
Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data—0
Generating near-infrared facial expression datasets with dimensional affect labels—0
Adversarial Backdoor Defense in CLIP—0
Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation—0
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look—0
Feature-based Style Randomization for Domain Generalization—0
Computational Ceramicology—0
Feature-level augmentation to improve robustness of deep neural networks to affine transformations—0
Feature-level Malware Obfuscation in Deep Learning—0
Feature Matching Data Synthesis for Non-IID Federated Learning—0
A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis—0
Generating Skyline Datasets for Data Science Models—0
Disfluency Detection with Unlabeled Data and Small BERT Models—0
Feature Space Transfer for Data Augmentation—0
Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data—0
Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification—0
Feature Weaken: Vicinal Data Augmentation for Classification—0
Bootstrapping User and Item Representations for One-Class Collaborative Filtering—0
A Novel Approach to WaveNet Architecture for RF Signal Separation with Learnable Dilation and Data Augmentation—0
Federated Contrastive Learning for Decentralized Unlabeled Medical Images—0
Federated Cross-Domain Click-Through Rate Prediction With Large Language Model Augmentation—0
Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization—0
Federated Domain Adaptation for ASR with Full Self-Supervision—0
Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks—0
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect—0
Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation—0
Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations—0
Disentangling style and content for low resource video domain adaptation: a case study on keystroke inference attacks—0
Bootstrapping a User-Centered Task-Oriented Dialogue System—0
A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education—0
AI-Augmented Thyroid Scintigraphy for Robust Classification—0
Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization—0
Bootstrapped Representation Learning for Skeleton-Based Action Recognition—0
FenceMask: A Data Augmentation Approach for Pre-extracted Image Features—0
Ferrograph image classification—0
Conditional Generation of Medical Images via Disentangled Adversarial Inference—0
Few-shot brain segmentation from weakly labeled data with deep heteroscedastic multi-task networks—0
Few-shot Class-incremental Learning for Cross-domain Disease Classification—0
An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset—0
Conditional Generative Adversarial Networks for Data Augmentation and Adaptation in Remotely Sensed Imagery—0
Conditional Generative Data Augmentation for Clinical Audio Datasets—0
3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing—0
Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation—0
Few-Shot Generation of Brain Tumors for Secure and Fair Data Sharing—0
Few-shot Hate Speech Detection Based on the MindSpore Framework—0
Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation—0
Generating Intermediate Steps for NLI with Next-Step Supervision—0
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems—0
Conditional set generation using Seq2seq models—0
Disease Severity Regression with Continuous Data Augmentation—0
Show:102550
← PrevPage 67 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