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 7201–7250 of 8378 papers

TitleStatusHype
Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image AnalysisCode1
CNN-based approach for glaucoma diagnosis using transfer learning and LBP-based data augmentation—0
Improving Generalization by Controlling Label-Noise Information in Neural Network WeightsCode1
Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos—0
Investigating an approach for low resource language dataset creation, curation and classification: Setswana and Sepedi—0
Dual-Attention GAN for Large-Pose Face FrontalizationCode1
Learning Robust Representations via Multi-View Information BottleneckCode1
Addressing the confounds of accompaniments in singer identificationCode1
Undersensitivity in Neural Reading Comprehension—0
SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data—0
CEB Improves Model RobustnessCode0
Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space—0
Feature-level Malware Obfuscation in Deep Learning—0
A Deep Learning Approach to Automate High-Resolution Blood Vessel Reconstruction on Computerized Tomography Images With or Without the Use of Contrast Agent—0
Task Augmentation by Rotating for Meta-LearningCode0
Snippext: Semi-supervised Opinion Mining with Augmented DataCode1
Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation—0
The Effect of Data Augmentation on Classification of Atrial Fibrillation in Short Single-Lead ECG Signals Using Deep Neural Networks—0
Data augmentation with Mobius transformationsCode1
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior—0
Learning Test-time Augmentation for Content-based Image Retrieval—0
Neural network with data augmentation in multi-objective prediction of multi-stage pump—0
On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use caseCode0
Radioactive data: tracing through trainingCode1
Revisiting Meta-Learning as Supervised Learning—0
Schema-Guided Dialogue State Tracking Task at DSTC8Code1
Efficient Model for Image Classification With Regularization TricksCode1
Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy—0
Data Augmentation for Histopathological Images Based on Gaussian-Laplacian Pyramid Blending—0
Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification FrameworksCode0
BUT Opensat 2019 Speech Recognition System—0
Real-Time Well Log Prediction From Drilling Data Using Deep Learning—0
FakeLocator: Robust Localization of GAN-Based Face Manipulations—0
Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses—0
Visualisation of Medical Image Fusion and Translation for Accurate Diagnosis of High Grade GliomasCode0
Model Averaging and Augmented Inference for Stable Echocardiography Segmentation using 2D ConvNets—0
Effect of GAN augmented dataset size on deep learning-based ultrasound bone segmentation model training—0
Morphological Signature for Improvement of Weakly Supervised Segmentation of Quadriceps Muscles on Magnetic Resonance Imaging Data—0
Red-GAN: Attacking class imbalance via conditioned generation. Yet another medical imaging perspectiveCode1
Data Techniques For Online End-to-end Speech Recognition—0
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methodsCode0
PDE-based Group Equivariant Convolutional Neural NetworksCode0
Semi-supervised ASR by End-to-end Self-training—0
Fish Detection Using Deep Learning—0
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data AugmentationCode0
Cloud and Cloud Shadow Segmentation for Remote Sensing Imagery via Filtered Jaccard Loss Function and Parametric AugmentationCode1
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard—0
Synthetic Magnetic Resonance Images with Generative Adversarial NetworksCode0
Interpreting Galaxy Deblender GAN from the Discriminator's Perspective—0
BSUV-Net: A Fully-Convolutional Neural Network forBackground Subtraction of Unseen VideosCode1
Show:102550
← PrevPage 145 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