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 6051–6100 of 8378 papers

TitleStatusHype
Data Augmentation with Variational Autoencoders and Manifold SamplingCode1
EfficientTDNN: Efficient Architecture Search for Speaker RecognitionCode1
Adversarial Imitation Learning with Trajectorial Augmentation and CorrectionCode0
AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersCode1
FakeMix Augmentation Improves Transparent Object DetectionCode0
Robust and Accurate Object Detection via Adversarial LearningCode3
An augmentation strategy to mimic multi-scanner variability in MRICode1
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual RecognitionCode1
Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations—0
Self-Supervised Pretraining Improves Self-Supervised PretrainingCode1
Implementation of CNN based COVID-19 classification model from CT imagesCode0
Efficient sign language recognition system and dataset creation method based on deep learning and image processing—0
Adversarial Feature Augmentation and Normalization for Visual RecognitionCode1
Progressive and Aligned Pose Attention Transfer for Person Image GenerationCode1
Adversarially Optimized Mixup for Robust Classification—0
MogFace: Towards a Deeper Appreciation on Face DetectionCode1
Local Patch AutoAugment with Multi-Agent CollaborationCode1
ModulOM: Disseminating Deep Learning Research with Modular Output MathematicsCode0
Image Synthesis for Data Augmentation in Medical CT using Deep Reinforcement Learning—0
Stride and Translation Invariance in CNNs—0
TrivialAugment: Tuning-free Yet State-of-the-Art Data AugmentationCode1
Temporal Cluster Matching for Change Detection of Structures from Satellite ImageryCode1
Training GANs with Stronger Augmentations via Contrastive DiscriminatorCode1
Reweighting Augmented Samples by Minimizing the Maximal Expected LossCode0
Pushing the Limits of Capsule NetworksCode1
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge DistillationCode1
Semi-supervised learning by selective training with pseudo labels via confidence estimation—0
Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics ModelCode1
XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition—0
Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving—0
Principled Ultrasound Data Augmentation for Classification of Standard Planes—0
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum LearningCode1
Robust 2D/3D Vehicle Parsing in CVIS—0
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks—0
Fair Mixup: Fairness via InterpolationCode1
Intraclass clustering: an implicit learning ability that regularizes DNNsCode0
BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification—0
S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning—0
Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks—0
Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance—0
Doubly Contrastive Deep ClusteringCode1
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object DetectionCode1
Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural NetworkCode0
Data augmentation by morphological mixup for solving Raven's Progressive Matrices—0
Multitask 3D CBCT-to-CT Translation and Organs-at-Risk Segmentation Using Physics-Based Data AugmentationCode1
Simplicial RegularizationCode0
Contemplating real-world object classificationCode1
CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 DetectionCode0
Consistency Regularization for Adversarial RobustnessCode1
Analysis of Convolutional Decoder for Image Caption Generation—0
Show:102550
← PrevPage 122 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