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 8276–8300 of 8378 papers

TitleStatusHype
Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation—0
AFFACT - Alignment-Free Facial Attribute Classification Technique—0
Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search—0
S3Pool: Pooling with Stochastic Spatial SamplingCode0
Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting—0
Automatic recognition of child speech for robotic applications in noisy environments—0
Variational Bayes In Private Settings (VIPS)Code0
A data augmentation methodology for training machine/deep learning gait recognition algorithms—0
From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips—0
Deep Fruit Detection in Orchards—0
Multiple Instance Learning Convolutional Neural Networks for Object Recognition—0
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum StructureCode0
X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets—0
A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image—0
Understanding data augmentation for classification: when to warp?—0
Sampling Generative NetworksCode1
Learning Bayesian Networks with Incomplete Data by Augmentation—0
Softplus Regressions and Convex Polytopes—0
CrowdNet: A Deep Convolutional Network for Dense Crowd CountingCode0
Generating Synthetic Data for Text RecognitionCode0
Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound ClassificationCode0
Fusing Deep Convolutional Networks for Large Scale Visual Concept Classification—0
Improving Temporal Relation Extraction with Training Instance Augmentation—0
The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task—0
MetaMind Neural Machine Translation System for WMT 2016—0
Show:102550
← PrevPage 332 of 336Next →
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 2×96d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified