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
UNICON: Unsupervised Intent Discovery via Semantic-level Contrastive Learning—0
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling—0
Unifying Graph Contrastive Learning via Graph Message Augmentation—0
Unifying Input and Output Smoothing in Neural Machine Translation—0
Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection—0
UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection—0
Universal Adaptive Data Augmentation—0
Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation—0
Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks—0
Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges—0
Unleashing the Power of Depth and Pose Estimation Neural Networks by Designing Compatible Endoscopic Images—0
Unlocking Robust Segmentation Across All Age Groups via Continual Learning—0
Unproportional mosaicing—0
Unshuffling Data for Improved Generalization—0
Unsupervised Adversarial Invariance—0
Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model—0
Unsupervised Coordinate-Based Video Denoising—0
Unsupervised Cross-Modality Domain Adaptation for Segmenting Vestibular Schwannoma and Cochlea with Data Augmentation and Model Ensemble—0
Unsupervised cross-user adaptation in taste sensation recognition based on surface electromyography with conformal prediction and domain regularized component analysis—0
Unsupervised Data Augmentation for Aspect Based Sentiment Analysis—0
Unsupervised Data Augmentation for Less-Resourced Languages with no Standardized Spelling—0
Unsupervised data augmentation for object detection—0
Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data—0
Unsupervised Data Validation Methods for Efficient Model Training—0
Unsupervised Deformable Ultrasound Image Registration and Its Application for Vessel Segmentation—0
Unsupervised Disentanglement of Linear-Encoded Facial Semantics—0
Unsupervised Document Embedding via Contrastive Augmentation—0
Unsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment—0
Unsupervised Domain Adaptation for RF-based Gesture Recognition—0
Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos—0
Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach—0
Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation—0
Unsupervised Domain Adaptation using Generative Models and Self-ensembling—0
Unsupervised Event Outlier Detection in Continuous Time—0
Unsupervised feature learning by augmenting single images—0
Unsupervised Feature Learning for Environmental Sound Classification Using Weighted Cycle-Consistent Generative Adversarial Network—0
Unsupervised Gaze-aware Contrastive Learning with Subject-specific Condition—0
Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals—0
Unsupervised Learning of Dense Visual Representations—0
Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation—0
Unsupervised Paraphrase Generation using Pre-trained Language Models—0
Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition—0
Unsupervised Prompt Tuning for Text-Driven Object Detection—0
Unsupervised Singing Voice Conversion—0
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations—0
Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal—0
Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos—0
Unsupervised Transfer Learning via Adversarial Contrastive Training—0
Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition—0
Untapped Potential of Data Augmentation: A Domain Generalization Viewpoint—0
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