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 8101–8150 of 8378 papers

TitleStatusHype
Learning Bayesian Networks with Incomplete Data by Augmentation—0
Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation—0
Learning Compositional Visual Concepts with Mutual Consistency—0
Learning Contraction Policies from Offline Data—0
Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition—0
Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks—0
Learning Data Manifolds with a Cutting Plane Method—0
Learning Dense Wide Baseline Stereo Matching for People—0
Learning Domain Invariant Representations for Generalizable Person Re-Identification—0
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings—0
Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation—0
Learning for Counterfactual Fairness from Observational Data—0
Learning from Data-Rich Problems: A Case Study on Genetic Variant Calling—0
Learning from Few Samples: A Survey—0
Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding—0
Learning from One Continuous Video Stream—0
Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga—0
Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations—0
Learning Human Perception Dynamics for Informative Robot Communication—0
Learning Instance-Specific Adaptation for Cross-Domain Segmentation—0
Learning Invariances using the Marginal Likelihood—0
Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding—0
Learning linear modules in a dynamic network with missing node observations—0
Learning Linear Symmetries in Data Using Moment Matching—0
Learning Loss for Test-Time Augmentation—0
Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images—0
Learning More with Less: GAN-based Medical Image Augmentation—0
Learning Neural Light Transport—0
Learning Noise-Invariant Representations for Robust Speech Recognition—0
Learning Noise-Invariant Representations for Robust Speech Recognition—0
Learning Noise-Robust Stable Koopman Operator for Control with Hankel DMD—0
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM—0
Learning Object Placement by Inpainting for Compositional Data Augmentation—0
Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training—0
Learning Physical Common Sense as Knowledge Graph Completion via BERT Data Augmentation and Constrained Tucker Factorization—0
Learning Polynomial Problems with SL(2,R) Equivariance—0
Learning Pose Grammar for Monocular 3D Pose Estimation—0
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge—0
Learning Robust Feature Representations for Scene Text Detection—0
Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks—0
Learning Sequential Information in Task-based fMRI for Synthetic Data Augmentation—0
Learning Temporal Embeddings for Complex Video Analysis—0
Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization—0
Learning the Non-linearity in Convolutional Neural Networks—0
Learning to Ask Unanswerable Questions for Machine Reading Comprehension—0
Learning to Augment for Casual User Recommendation—0
Learning to Augment Influential Data—0
Learning to Augment via Implicit Differentiation for Domain Generalization—0
Learning to Detect Every Thing in an Open World—0
Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis—0
Show:102550
← PrevPage 163 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