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 6201–6250 of 8378 papers

TitleStatusHype
Efficient-CapsNet: Capsule Network with Self-Attention RoutingCode1
Speech Enhancement for Wake-Up-Word detection in Voice Assistants—0
Enhancing Sequence-to-Sequence Neural Lemmatization with External ResourcesCode0
ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification—0
BirdNET: A deep learning solution for avian diversity monitoringCode2
A Multi-Scale Conditional Deep Model for Tumor Cell Ratio Counting—0
On the Importance of Capturing a Sufficient Diversity of Perspective for the Classification of micro-PCBsCode0
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel PairsCode1
El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing—0
TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and MetricsCode1
Spatio-temporal Data Augmentation for Visual Surveillance—0
Facilitating Terminology Translation with Target Lemma AnnotationsCode0
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation—0
Towards a Better Integration of Fuzzy Matches in Neural Machine Translation through Data AugmentationCode1
EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery ClassificationCode1
A Pressure Ulcer Care System For Remote Medical Assistance: Residual U-Net with an Attention Model Based for Wound Area Segmentation—0
Automatic Cerebral Vessel Extraction in TOF-MRA Using Deep Learning—0
Rethinking Domain Generalization Baselines—0
Maximum Likelihood Training of Score-Based Diffusion ModelsCode1
DataLoc+: A Data Augmentation Technique for Machine Learning in Room-Level Indoor Localization—0
Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning MethodCode1
Distilling Large Language Models into Tiny and Effective Students using pQRNN—0
A Person Re-identification Data Augmentation Method with Adversarial Defense EffectCode1
Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation—0
Class balanced underwater object detection dataset generated by class-wise style augmentation—0
Deep Convolutional Autoencoders for reconstructing magnetic resonance images of the healthy brainCode1
An Empirical Study and Analysis on Open-Set Semi-Supervised Learning—0
Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transferCode0
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous DatasetsCode1
Learning Visual Representations with Optimum-Path Forest and its Applications to Barrett's Esophagus and Adenocarcinoma Diagnosis—0
On Data-Augmentation and Consistency-Based Semi-Supervised Learning—0
TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors—0
Removing Undesirable Feature Contributions Using Out-of-Distribution DataCode0
Improve Global Glomerulosclerosis Classification with Imbalanced Data using CircleMix AugmentationCode0
GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving—0
Adversarial cycle-consistent synthesis of cerebral microbleeds for data augmentation—0
Motion-Based Handwriting RecognitionCode0
Text Augmentation in a Multi-Task View—0
Random Shadows and Highlights: A new data augmentation method for extreme lighting conditionsCode1
Sequential IoT Data Augmentation using Generative Adversarial Networks—0
Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records—0
Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation—0
Memory-Augmented Reinforcement Learning for Image-Goal NavigationCode1
Random Transformation of Image Brightness for Adversarial AttackCode0
Data augmentation and feature selection for automatic model recommendation in computational physics—0
Mixup Without HesitationCode1
Analysis of skin lesion images with deep learningCode1
Remote Pulse Estimation in the Presence of Face Masks—0
Transfer Learning and Augmentation for Word Sense Disambiguation—0
Towards Domain Invariant Single Image Dehazing—0
Show:102550
← PrevPage 125 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