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 6751–6800 of 8378 papers

TitleStatusHype
Anchor-free Small-scale Multispectral Pedestrian DetectionCode1
A Data-Efficient Deep Learning Based Smartphone Application For Detection Of Pulmonary Diseases Using Chest X-rays—0
Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training—0
Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences—0
Robust Handwriting Recognition with Limited and Noisy Data—0
StoRIR: Stochastic Room Impulse Response Generation for Audio Data AugmentationCode1
BUT-FIT at SemEval-2020 Task 4: Multilingual commonsenseCode0
Cross-Modality 3D Object Detection—0
Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View SynthesisCode0
A Deep Convolutional Neural Network for the Detection of Polyps in Colonoscopy Images—0
Model Patching: Closing the Subgroup Performance Gap with Data AugmentationCode1
Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data—0
Optimized Deep Encoder-Decoder Methods for Crack Segmentation—0
Adaptation Algorithms for Neural Network-Based Speech Recognition: An OverviewCode0
PointMixup: Augmentation for Point CloudsCode1
Learning Temporally Invariant and Localizable Features via Data Augmentation for Video RecognitionCode1
Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling—0
Improving the Performance of Fine-Grain Image Classifiers via Generative Data Augmentation—0
Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams—0
Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms—0
PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks—0
Transformer with Bidirectional Decoder for Speech Recognition—0
Spatiotemporal Contrastive Video Representation LearningCode1
Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification—0
Deep Robust Clustering by Contrastive LearningCode1
Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source SeparationCode1
On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation—0
Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation—0
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognitionCode1
Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way—0
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANCode1
NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual TransferCode1
Spherical Feature Transform for Deep Metric Learning—0
From Human Mesenchymal Stromal Cells to Osteosarcoma Cells Classification by Deep Learning—0
Autoencoder Image Interpolation by Shaping the Latent Space—0
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization—0
Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery—0
Generalisable Cardiac Structure Segmentation via Attentional and Stacked Image Adaptation—0
Adversarial Semantic Data Augmentation for Human Pose EstimationCode1
Multimodal Semi-supervised Learning Framework for Punctuation Prediction in Conversational Speech—0
Removing Backdoor-Based Watermarks in Neural Networks with Limited Data—0
LungRN+NL: An Improved Adventitious Lung Sound Classification Using Non-Local Block ResNet Neural Network with Mixup Data Augmentation—0
Adversarial Data Augmentation via Deformation Statistics—0
Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model—0
Towards Automated Testing and Robustification by Semantic Adversarial Data Generation—0
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler—0
Learning Object Placement by Inpainting for Compositional Data Augmentation—0
AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning—0
Generative View-Correlation Adaptation for Semi-Supervised Multi-View Learning—0
Joint Generative Learning and Super-Resolution For Real-World Camera-Screen Degradation—0
Show:102550
← PrevPage 136 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