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 5401–5450 of 8378 papers

TitleStatusHype
Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape ModelCode0
Data Augmentation for Biomedical Factoid Question AnsweringCode0
CrudeOilNews: An Annotated Crude Oil News Corpus for Event ExtractionCode0
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation LearningCode0
Frequency Selective Augmentation for Video Representation Learning—0
Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition—0
The Effects of Regularization and Data Augmentation are Class Dependent—0
Surface Vision Transformers: Flexible Attention-Based Modelling of Biomedical Surfaces—0
Multi-Sample ζ-mixup: Richer, More Realistic Synthetic Samples from a p-Series Interpolant—0
CoCoSoDa: Effective Contrastive Learning for Code Search—0
Banana Sub-Family Classification and Quality Prediction using Computer Vision—0
Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization—0
Using Synthetic Data for Conversational Response Generation in Low-resource Settings—0
DAGAM: Data Augmentation with Generation And ModificationCode0
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation—0
Fact Checking with Insufficient EvidenceCode0
Mixing Signals: Data Augmentation Approach for Deep Learning Based Modulation Recognition—0
Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low DataCode0
Learning Linear Symmetries in Data Using Moment Matching—0
Learning to Augment for Casual User Recommendation—0
A Dual-Contrastive Framework for Low-Resource Cross-Lingual Named Entity RecognitionCode0
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition—0
Selecting task with optimal transport self-supervised learning for few-shot classification—0
Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer SensorsCode0
SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks—0
Text-To-Speech Data Augmentation for Low Resource Speech Recognition—0
CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection—0
SimVQA: Exploring Simulated Environments for Visual Question Answering—0
SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy—0
A Survey of Robust 3D Object Detection Methods in Point Clouds—0
Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension—0
Federated Domain Adaptation for ASR with Full Self-Supervision—0
Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels—0
Learning Instance-Specific Adaptation for Cross-Domain Segmentation—0
Supervised Graph Contrastive Learning for Few-shot Node Classification—0
Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation MapCode0
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing—0
Physics-informed deep-learning applications to experimental fluid mechanics—0
Improving Persian Relation Extraction Models by Data Augmentation—0
Neural representation of a time optimal, constant acceleration rendezvous—0
Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure—0
Leveraging Clinically Relevant Biometric Constraints To Supervise A Deep Learning Model For The Accurate Caliper Placement To Obtain Sonographic Measurements Of The Fetal Brain—0
Robust Speaker Recognition with Transformers Using wav2vec 2.0—0
Improved singing voice separation with chromagram-based pitch-aware remixing—0
Hierarchical Transformer Model for Scientific Named Entity RecognitionCode0
Towards physiology-informed data augmentation for EEG-based BCIs—0
bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media CommentsCode0
A Spiking Neural Network based on Neural Manifold for Augmenting Intracortical Brain-Computer Interface Data—0
Metropolis-Hastings Data Augmentation for Graph Neural Networks—0
How Do We Fail? Stress Testing Perception in Autonomous VehiclesCode0
Show:102550
← PrevPage 109 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