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 5601–5650 of 8378 papers

TitleStatusHype
Discriminative Reranking for Neural Machine Translation—0
LeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation—0
Rethinking Stealthiness of Backdoor Attack against NLP ModelsCode1
OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification—0
Data Augmentation with Adversarial Training for Cross-Lingual NLI—0
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question UnderstandingCode1
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes—0
DeepBlueAI at SemEval-2021 Task 1: Lexical Complexity Prediction with A Deep Ensemble Approach—0
Cambridge at SemEval-2021 Task 2: Neural WiC-Model with Data Augmentation and Exploration of Representation—0
LIORI at SemEval-2021 Task 2: Span Prediction and Binary Classification approaches to Word-in-Context Disambiguation—0
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation—0
PAW at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation : Exploring Cross Lingual Transfer, Augmentations and Adversarial Training—0
An Effective and Robust Detector for Logo DetectionCode1
Missingness Augmentation: A General Approach for Improving Generative Imputation ModelsCode0
Real-time Streaming Perception System for Autonomous Driving—0
Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks—0
Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness—0
Nonparametric posterior learning for emission tomography with multimodal data—0
Addressing materials' microstructure diversity using transfer learning—0
Term Expansion and FinBERT fine-tuning for Hypernym and Synonym Ranking of Financial TermsCode0
An explainable two-dimensional single model deep learning approach for Alzheimer's disease diagnosis and brain atrophy localization—0
Deep learning based cough detection camera using enhanced features—0
Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings—0
Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint OptimizationCode1
CarveNet: Carving Point-Block for Complex 3D Shape Completion—0
Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach—0
Neural Style Transfer Enhanced Training Support For Human Activity Recognition—0
CCGL: Contrastive Cascade Graph LearningCode1
Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation—0
A Tale Of Two Long TailsCode0
Deep Variational Models for Collaborative Filtering-based Recommender SystemsCode0
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Benign Adversarial Attack: Tricking Models for Goodness—0
Augmentation Pathways Network for Visual RecognitionCode0
Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument soundsCode0
Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition—0
Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks—0
Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline InvestigationCode1
Human Pose Transfer with Augmented Disentangled Feature Consistency—0
A3GC-IP: Attention-Oriented Adjacency Adaptive Recurrent Graph Convolutions for Human Pose Estimation from Sparse Inertial Measurements—0
Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image SegmentationCode0
Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech—0
Improving Polyphonic Sound Event Detection on Multichannel Recordings with the Sørensen-Dice Coefficient Loss and Transfer Learning—0
Improve Learning from Crowds via Generative Augmentation—0
Geometric Data Augmentation Based on Feature Map Ensemble—0
An overview of mixing augmentation methods and augmentation strategies—0
TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor SegmentationCode1
Paraphrasing via Ranking Many Candidates—0
Built-in Elastic Transformations for Improved Robustness—0
A Bayesian Approach to Invariant Deep Neural Networks—0
Show:102550
← PrevPage 113 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