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 4951–5000 of 8378 papers

TitleStatusHype
Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models—0
On the Cross-dataset Generalization in License Plate RecognitionCode1
MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object DetectionCode1
SS3D: Sparsely-Supervised 3D Object Detection From Point Cloud—0
Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection—0
Semi-Supervised Few-Shot Learning via Multi-Factor ClusteringCode0
Distillation Using Oracle Queries for Transformer-Based Human-Object Interaction Detection—0
LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection—0
CADTransformer: Panoptic Symbol Spotting Transformer for CAD DrawingsCode1
Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and BeyondCode1
Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor DataCode1
Evaluating Deep Music Generation Methods Using Data Augmentation—0
Towards Robustness of Neural Networks—0
LINDA: Unsupervised Learning to Interpolate in Natural Language Processing—0
Uncertainty Detection and Reduction in Neural Decoding of EEG SignalsCode0
Generation of Synthetic Rat Brain MRI scans with a 3D Enhanced Alpha-GAN—0
PRIME: A few primitives can boost robustness to common corruptionsCode1
Acoustic scene classification using auditory datasetsCode0
Self-Supervised Graph Representation Learning for Neuronal Morphologies—0
Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition—0
TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations—0
BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-ViewCode2
Crash Data Augmentation Using Conditional Generative Adversarial Networks (CGAN) for Improving Safety Performance Functions—0
Improving Robustness with Image Filtering—0
PRONTO: Preamble Overhead Reduction with Neural Networks for Coarse SynchronizationCode0
MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and GroundingCode1
Data Augmentation for Mental Health Classification on Social Media—0
Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement LearningCode0
Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey—0
Watermarking Images in Self-Supervised Latent SpacesCode1
High Fidelity Visualization of What Your Self-Supervised Representation Knows AboutCode1
How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation—0
Mitigating the Bias of Centered Objects in Common Datasets—0
ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification—0
Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel ModelCode0
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise ImagesCode1
Deep Hash Distillation for Image RetrievalCode1
Bioacoustic Event Detection with prototypical networks and data augmentation—0
Multiple Instance Learning for Brain Tumor Detection from Magnetic Resonance Spectroscopy Data—0
Improved YOLOv5 network for real-time multi-scale traffic sign detectionCode0
DG2: Data Augmentation Through Document Grounded Dialogue Generation—0
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed ClassificationCode1
Invariance Through Latent Alignment—0
Maximum Bayes Smatch Ensemble Distillation for AMR ParsingCode0
Improving Compositional Generalization with Latent Structure and Data AugmentationCode1
ImportantAug: a data augmentation agent for speechCode0
Handwritten text generation and strikethrough characters augmentation—0
Improving COVID-19 CXR Detection with Synthetic Data Augmentation—0
On the use of Cortical Magnification and Saccades as Biological Proxies for Data AugmentationCode1
CT4Rec: Simple yet Effective Consistency Training for Sequential RecommendationCode1
Show:102550
← PrevPage 100 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