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 6851–6900 of 8378 papers

TitleStatusHype
DMix: Distance Constrained Interpolative Mixup—0
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition—0
Do CNNs Encode Data Augmentations?—0
Document Image Layout Analysis via Explicit Edge Embedding Network—0
Document-level Event Factuality Identification via Machine Reading Comprehension Frameworks with Transfer Learning—0
Does Data Augmentation Benefit from Split BatchNorms—0
Does Data Augmentation Lead to Positive Margin?—0
Does enhanced shape bias improve neural network robustness to common corruptions?—0
Does equivariance matter at scale?—0
Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers—0
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification—0
Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?—0
Does Synthetic Data Make Large Language Models More Efficient?—0
Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?—0
Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration—0
Domain Adaptive Cascade R-CNN for MItosis DOmain Generalization (MIDOG) Challenge—0
Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization—0
Domain-Agnostic Clustering with Self-Distillation—0
Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation—0
Domain Gap Embeddings for Generative Dataset Augmentation—0
Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)—0
Domain Generalization -- A Causal Perspective—0
Domain Generalization: A Survey—0
Domain Generalization Emerges from Dreaming—0
Domain Generalization for In-Orbit 6D Pose Estimation—0
Domain generalization for retinal vessel segmentation via Hessian-based vector field—0
Domain generalization in fetal brain MRI segmentation \ multi-reconstruction augmentation—0
Domain Generalization via Balancing Training Difficulty and Model Capability—0
Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction—0
Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer—0
Domain-guided data augmentation for deep learning on medical imaging—0
Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection—0
Domain-specific augmentations with resolution agnostic self-attention mechanism improves choroid segmentation in optical coherence tomography images—0
Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization—0
Domain specificity and data efficiency in typo tolerant spell checkers: the case of search in online marketplaces—0
Domain Transfer based Data Augmentation for Neural Query Translation—0
Dominant Shuffle: A Simple Yet Powerful Data Augmentation for Time-series Prediction—0
Don't overfit the history -- Recursive time series data augmentation—0
DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN—0
Do We Need to Differentiate Negative Candidates Before Training a Neural Ranker?—0
Alleviating Mode Collapse in GAN via Diversity Penalty Module—0
DRAC: Diabetic Retinopathy Analysis Challenge with Ultra-Wide Optical Coherence Tomography Angiography Images—0
Draft, Command, and Edit: Controllable Text Editing in E-Commerce—0
Draft, Command, and Edit: Controllable Text Editing in E-Commerce—0
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error—0
DRDr: Automatic Masking of Exudates and Microaneurysms Caused By Diabetic Retinopathy Using Mask R-CNN and Transfer Learning—0
DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers—0
Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction—0
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation—0
DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images—0
Show:102550
← PrevPage 138 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