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

Showing 71017150 of 8378 papers

TitleStatusHype
Joint translation and unit conversion for end-to-end localization0
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data AugmentationCode1
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic SegmentationCode1
Injecting Numerical Reasoning Skills into Language ModelsCode1
Feature Re-Learning with Data Augmentation for Video Relevance PredictionCode1
A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic modelsCode0
Transfer learning and subword sampling for asymmetric-resource one-to-many neural translationCode0
Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair GenerationCode0
SA-UNet: Spatial Attention U-Net for Retinal Vessel SegmentationCode1
Pyramid Focusing Network for mutation prediction and classification in CT images0
Re-translation versus Streaming for Simultaneous Translation0
Inspector Gadget: A Data Programming-based Labeling System for Industrial Images0
Probabilistic Spatial Transformer NetworksCode0
Dense Residual Network for Retinal Vessel SegmentationCode1
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition0
Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation0
Incorporating Bilingual Dictionaries for Low Resource Semi-Supervised Neural Machine Translation0
CNN-MoE based framework for classification of respiratory anomalies and lung disease detection0
ObjectNet Dataset: Reanalysis and CorrectionCode1
Quantifying Data Augmentation for LiDAR based 3D Object Detection0
Cell Segmentation by Combining Marker-Controlled Watershed and Deep LearningCode0
The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment0
Improving 3D Object Detection through Progressive Population Based Augmentation0
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyCode1
Deep Entity Matching with Pre-Trained Language ModelsCode1
Physically Realizable Adversarial Examples for LiDAR Object Detection0
Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning0
UniformAugment: A Search-free Probabilistic Data Augmentation ApproachCode1
Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation0
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement0
Generative Latent Implicit Conditional Optimization when Learning from Small SampleCode1
Low resource language dataset creation, curation and classification: Setswana and Sepedi -- Extended Abstract0
Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images0
Adversarial Feature Hallucination Networks for Few-Shot LearningCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification0
A Close Look at Deep Learning with Small Data0
Gradient-based Data Augmentation for Semi-Supervised Learning0
Efficient Domain Generalization via Common-Specific Low-Rank DecompositionCode1
Lightweight Photometric Stereo for Facial Details RecoveryCode1
Fashion Landmark Detection and Category Classification for RoboticsCode0
Instance Credibility Inference for Few-Shot LearningCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation0
Fast Cross-domain Data Augmentation through Neural Sentence Editing0
On Calibration of Mixup Training for Deep Neural NetworksCode0
ARDA: Automatic Relational Data Augmentation for Machine LearningCode0
Acoustic Scene Classification with Squeeze-Excitation Residual Networks0
RADIOGAN: Deep Convolutional Conditional Generative adversarial Network To Generate PET Images0
Local Rotation Invariance in 3D CNNsCode0
Show:102550
← PrevPage 143 of 168Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6Unverified
5ResNet-200 (UA)Accuracy (%)80.4Unverified
6ResNet-200 (AA)Accuracy (%)80Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified