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 6851–6900 of 8378 papers

TitleStatusHype
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation—0
Persian Handwritten Digit, Character and Word Recognition Using Deep Learning—0
A Study of Transfer Learning in Music Source Separation—0
Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition—0
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering—0
Improving Robustness by Augmenting Training Sentences with Predicate-Argument StructuresCode0
Towards Robust Neural Networks via Orthogonal DiversityCode0
Learning Loss for Test-Time Augmentation—0
Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data—0
Logic Guided Genetic Algorithms—0
Learning Curves for Analysis of Deep NetworksCode0
KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision—0
How Data Augmentation affects Optimization for Linear Regression—0
Sentence Boundary Augmentation For Neural Machine Translation Robustness—0
Controllable Text Simplification with Explicit Paraphrasing—0
Action Sequence Augmentation for Early Graph-based Anomaly DetectionCode0
Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020—0
Introducing and Applying Newtonian Blurring: An Augmented Dataset of 126,000 Human Connectomes at braingraph.org—0
Combining Ensembles and Data Augmentation can Harm your Calibration—0
MicAugment: One-shot Microphone Style TransferCode0
ColloQL: Robust Cross-Domain Text-to-SQL Over Search QueriesCode0
Multi-Window Data Augmentation Approach for Speech Emotion Recognition—0
Image-based Automated Species Identification: Can Virtual Data Augmentation Overcome Problems of Insufficient Sampling?—0
CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding—0
Detecting ESG topics using domain-specific language models and data augmentation approaches—0
Adaptive Feature Selection for End-to-End Speech Translation—0
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering—0
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring TasksCode0
Pose And Joint-Aware Action RecognitionCode0
Reconstructing A Large Scale 3D Face Dataset for Deep 3D Face Identification—0
Peer-Assisted Robotic Learning: A Data-Driven Collaborative Learning Approach for Cloud Robotic Systems—0
Revisiting Optical Flow Estimation in 360 Videos—0
A Transformer Based Pitch Sequence Autoencoder with MIDI Augmentation—0
Does Data Augmentation Benefit from Split BatchNorms—0
3D Segmentation Networks for Excessive Numbers of Classes: Distinct Bone Segmentation in Upper Bodies—0
Ferrograph image classification—0
EPYNET: Efficient Pyramidal Network for Clothing Segmentation—0
Land Cover Semantic Segmentation Using ResUNet—0
Towards Data-efficient Modeling for Wake Word Spotting—0
Monitoring War Destruction from Space: A Machine Learning Approach—0
Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy—0
Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers—0
Pedestrian Trajectory Prediction with Convolutional Neural Networks—0
EFSG: Evolutionary Fooling Sentences Generator—0
Improving Low Resource Code-switched ASR using Augmented Code-switched TTS—0
Chatbot Interaction with Artificial Intelligence: Human Data Augmentation with T5 and Language Transformer Ensemble for Text Classification—0
PHICON: Improving Generalization of Clinical Text De-identification Models via Data AugmentationCode0
Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Network—0
Category-Learning with Context-Augmented Autoencoder—0
How Does Mixup Help With Robustness and Generalization?—0
Show:102550
← PrevPage 138 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