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 3051–3100 of 8378 papers

TitleStatusHype
Food Image Recognition by Using Convolutional Neural Networks (CNNs)Code0
FormulaReasoning: A Dataset for Formula-Based Numerical ReasoningCode0
Flareon: Stealthy any2any Backdoor Injection via Poisoned AugmentationCode0
Exploring Inconsistent Knowledge Distillation for Object Detection with Data AugmentationCode0
Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference ModelsCode0
Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI FeedbackCode0
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex OptimizationCode0
Noise-Agnostic Quantum Error Mitigation with Data Augmented Neural ModelsCode0
FiNLP at FinCausal 2020 Task 1: Mixture of BERTs for Causal Sentence Identification in Financial TextsCode0
First-Order Manifold Data Augmentation for Regression LearningCode0
Flexible framework for generating synthetic electrocardiograms and photoplethysmogramsCode0
Automatic Assignment of Radiology Examination Protocols Using Pre-trained Language Models with Knowledge DistillationCode0
Automatically Learning Data Augmentation Policies for Dialogue TasksCode0
Automatically Identifying Language Family from Acoustic Examples in Low Resource ScenariosCode0
Data augmentation instead of explicit regularizationCode0
FilipN@LT-EDI-ACL2022-Detecting signs of Depression from Social Media: Examining the use of summarization methods as data augmentation for text classificationCode0
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy InterpolationCode0
Revisiting Data Augmentation in Deep Reinforcement LearningCode0
Fill the GAP: Exploiting BERT for Pronoun ResolutionCode0
Few-shot learning for COVID-19 Chest X-Ray Classification with Imbalanced Data: An Inter vs. Intra Domain StudyCode0
Few-shot learning through contextual data augmentationCode0
Few-Shot Continual Learning via Flat-to-Wide ApproachesCode0
Analysis and Optimization of Convolutional Neural Network ArchitecturesCode0
Few-shot learning via tensor hallucinationCode0
Achieving Verified Robustness to Symbol Substitutions via Interval Bound PropagationCode0
Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment AnalysisCode0
Data Augmentation Generative Adversarial NetworksCode0
Data Augmentation for Object Detection via Progressive and Selective Instance-SwitchingCode0
Few-Shot Class Incremental Learning via Robust Transformer ApproachCode0
Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric LearningCode0
Classification robustness to common optical aberrationsCode0
Robust Asymmetric Heterogeneous Federated Learning with Corrupted ClientsCode0
Fine Tuning vs. Retrieval Augmented Generation for Less Popular KnowledgeCode0
Analysing the Robustness of Dual Encoders for Dense Retrieval Against MisspellingsCode0
Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural NetworksCode0
Feature transforms for image data augmentationCode0
Feature Expansion and enhanced Compression for Class Incremental LearningCode0
FastIF: Scalable Influence Functions for Efficient Model Interpretation and DebuggingCode0
Automated Lay Language Summarization of Biomedical Scientific ReviewsCode0
Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso RegressionCode0
Faster AutoAugment: Learning Augmentation Strategies using BackpropagationCode0
Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative StudyCode0
Artificial Intelligence for Biomedical Video GenerationCode0
FaultFormer: Pretraining Transformers for Adaptable Bearing Fault ClassificationCode0
Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AICode0
FAST-AID Brain: Fast and Accurate Segmentation Tool using Artificial Intelligence Developed for BrainCode0
Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networksCode0
Data Augmentation for Skin Lesion AnalysisCode0
Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained ModelCode0
FakeMix Augmentation Improves Transparent Object DetectionCode0
Show:102550
← PrevPage 62 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 2×96d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified