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 83018350 of 8378 papers

TitleStatusHype
Adjusting for Dropout Variance in Batch Normalization and Weight InitializationCode0
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild0
Improved Recurrent Neural Networks for Session-based Recommendations0
3D U-Net: Learning Dense Volumetric Segmentation from Sparse AnnotationCode1
DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification0
Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark0
DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs0
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning0
Deep neural networks are robust to weight binarization and other non-linear distortions0
Sketch Me That Shoe0
Adversarial Diversity and Hard Positive Generation0
Designing a Speech Corpus for the Development and Evaluation of Dictation Systems in Latvian0
DisturbLabel: Regularizing CNN on the Loss LayerCode0
Automatic Graphic Logo Detection via Fast Region-based Convolutional Networks0
Real-Time Facial Segmentation and Performance Capture from RGB Input0
Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life RecordingsCode0
Character-Level Question Answering with AttentionCode0
Image Captioning with Deep Bidirectional LSTMsCode0
Data Augmentation via Levy ProcessesCode0
Exploiting Cyclic Symmetry in Convolutional Neural Networks0
Brain-Inspired Deep Networks for Image Aesthetics Assessment0
Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation0
Nonparametric Bayesian Factor Analysis for Dynamic Count Matrices0
Fast Parallel SVM using Data Augmentation0
Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation0
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings0
Towards Dropout Training for Convolutional Neural Networks0
On-line Recognition of Handwritten Mathematical Symbols0
What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks0
A Unified Gradient Regularization Family for Adversarial Examples0
Convolutional neural networks with low-rank regularizationCode1
Reducing Overfitting in Deep Networks by Decorrelating Representations0
Bayesian Analysis of Dynamic Linear Topic Models0
Weakly Supervised Deep Detection NetworksCode0
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation0
That's So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using \#petpeeve Tweets0
DeepWriterID: An End-to-end Online Text-independent Writer Identification System0
What is Holding Back Convnets for Detection?0
Dropout Training for SVMs with Data Augmentation0
Multimodal Deep Learning for Robust RGB-D Object RecognitionCode0
Manitest: Are classifiers really invariant?0
Towards Good Practices for Very Deep Two-Stream ConvNetsCode1
Soccer jersey number recognition using convolutional neural networks0
Dropout as data augmentation0
Deep CNN Ensemble with Data Augmentation for Object Detection0
Locally Adaptive Dynamic Networks0
Character-level Chinese Writer Identification using Path Signature Feature, DropStroke and Deep CNN0
APAC: Augmented PAttern Classification with Neural Networks0
Learning Temporal Embeddings for Complex Video Analysis0
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks0
Show:102550
← PrevPage 167 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