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

Showing 45514600 of 8378 papers

TitleStatusHype
FilipN@LT-EDI-ACL2022-Detecting signs of Depression from Social Media: Examining the use of summarization methods as data augmentation for text classificationCode0
DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes0
Seq2Path: Generating Sentiment Tuples as Paths of a Tree0
AMR-DA: Data Augmentation by Abstract Meaning RepresentationCode1
Convex Combination Consistency between Neighbors for Weakly-supervised Action LocalizationCode1
The use of Data Augmentation as a technique for improving neural network accuracy in detecting fake news about COVID-190
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness0
Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving0
Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem SolversCode0
Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI0
COVID-Net US-X: Enhanced Deep Neural Network for Detection of COVID-19 Patient Cases from Convex Ultrasound Imaging Through Extended Linear-Convex Ultrasound Augmentation LearningCode0
Human-in-the-loop online multi-agent approach to increase trustworthiness in ML models through trust scores and data augmentation0
Improving robustness of language models from a geometry-aware perspective0
A DOMAIN TRANSFER BASED DATA AUGMENTATION METHOD FOR AUTOMATED RESPIRATORY CLASSIFICATION0
Label Anchored Contrastive Learning for Language Understanding0
Deeper Insights into the Robustness of ViTs towards Common Corruptions0
Reprint: a randomized extrapolation based on principal components for data augmentationCode0
Disambiguation of morpho-syntactic features of African American English -- the case of habitual be0
Contrastive Learning for Knowledge TracingCode1
Data augmentation and multimodal learning for predicting drug response in patient-derived xenografts from gene expressions and histology imagesCode2
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization0
EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text ClassificationCode1
Universum-inspired Supervised Contrastive LearningCode0
TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla0
SoftEdge: Regularizing Graph Classification with Random Soft Edges0
The 2021 NIST Speaker Recognition Evaluation0
Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation0
Fast AdvPropCode1
SelfD: Self-Learning Large-Scale Driving Policies From the Web0
The NIST CTS Speaker Recognition Challenge0
Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation0
A Mobile Food Recognition System for Dietary Assessment0
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies0
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender SystemCode1
G2GT: Retrosynthesis Prediction with Graph to Graph Attention Neural Network and Self-TrainingCode0
Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models0
Image Data Augmentation for Deep Learning: A Survey0
Adaptive Noisy Data Augmentation for Regularized Estimation and Inference in Generalized Linear Models0
Gated Multimodal Fusion with Contrastive Learning for Turn-taking Prediction in Human-robot Dialogue0
UMass PCL at SemEval-2022 Task 4: Pre-trained Language Model Ensembles for Detecting Patronizing and Condescending Language0
Extracting Targeted Training Data from ASR Models, and How to Mitigate It0
Application of Transfer Learning and Ensemble Learning in Image-level Classification for Breast Histopathology0
UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data AugmentationCode1
A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression ComprehensionCode1
AFSC: Adaptive Fourier Space Compression for Anomaly Detection0
UFRC: A Unified Framework for Reliable COVID-19 Detection on Crowdsourced Cough Audio0
A Robust and Scalable Attention Guided Deep Learning Framework for Movement Quality Assessment0
A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment AnalysisCode1
STRATA: Word Boundaries & Phoneme Recognition From Continuous Urdu Speech using Transfer Learning, Attention, & Data Augmentation0
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive LearningCode1
Show:102550
← PrevPage 92 of 168Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6Unverified
5ResNet-200 (UA)Accuracy (%)80.4Unverified
6ResNet-200 (AA)Accuracy (%)80Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified