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 4151–4200 of 8378 papers

TitleStatusHype
Fault Detection and Classification of Aerospace Sensors using a VGG16-based Deep Neural Network—0
AADG: Automatic Augmentation for Domain Generalization on Retinal Image SegmentationCode1
Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety—0
Group DETR: Fast DETR Training with Group-Wise One-to-Many AssignmentCode1
Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition—0
Controllable User Dialogue Act Augmentation for Dialogue State TrackingCode0
Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis—0
Semi-Leak: Membership Inference Attacks Against Semi-supervised LearningCode1
Efficient Classification with Counterfactual Reasoning and Active LearningCode0
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth EstimationCode1
Training Robust Spiking Neural Networks on Neuromorphic Data with Spatiotemporal Fragments—0
Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks—0
Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence—0
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation—0
3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian LocalizationCode1
Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture—0
Enhancing Generative Networks for Chest Anomaly Localization through Automatic Registration-Based Unpaired-to-Pseudo-Paired Training Data Translation—0
SplitMixer: Fat Trimmed From MLP-like ModelsCode0
Tailoring Self-Supervision for Supervised LearningCode1
An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation—0
DC-BENCH: Dataset Condensation BenchmarkCode1
A Novel Neural Network Training Method for Autonomous Driving Using Semi-Pseudo-Labels and 3D Data Augmentations—0
Revisiting data augmentation for subspace clustering—0
Improving Data Driven Inverse Text Normalization using Data Augmentation—0
Towards Accurate and Robust Classification in Continuously Transitioning Industrial Sprays with Mixup—0
Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection—0
On the Usability of Transformers-based models for a French Question-Answering task—0
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain RobustnessCode1
WideResNet with Joint Representation Learning and Data Augmentation for Cover Song Identification—0
Research Trends and Applications of Data Augmentation AlgorithmsCode0
TokenMix: Rethinking Image Mixing for Data Augmentation in Vision TransformersCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
Classifying COVID-19 vaccine narratives—0
Rethinking Data Augmentation for Robust Visual Question AnsweringCode1
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANsCode1
Progress and limitations of deep networks to recognize objects in unusual posesCode1
Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting SystemCode0
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning—0
Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement LearningCode0
Towards Better Dermoscopic Image Feature Representation Learning for Melanoma ClassificationCode0
Classification of Bark Beetle-Induced Forest Tree Mortality using Deep LearningCode0
Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model—0
Universal Adaptive Data Augmentation—0
Attention, Filling in The Gaps for Generalization in Routing Problems—0
Deepfake Video Detection with Spatiotemporal Dropout Transformer—0
Data Augmentation for Low-Resource Quechua ASR Improvement—0
Developing a Component Comment Extractor from Product Reviews on E-Commerce Sites—0
Efficient Augmentation for Imbalanced Deep LearningCode0
Fine-tuning Partition-aware Item Similarities for Efficient and Scalable RecommendationCode0
Self-supervised Group Meiosis Contrastive Learning for EEG-Based Emotion RecognitionCode1
Show:102550
← PrevPage 84 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