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 80018050 of 8378 papers

TitleStatusHype
CMMC-BDRC Solution to the NLP-TEA-2018 Chinese Grammatical Error Diagnosis Task0
Semantically Equivalent Adversarial Rules for Debugging NLP modelsCode0
Shape-from-Mask: A Deep Learning Based Human Body Shape Reconstruction from Binary Mask Images0
Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks0
HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsulesCode0
Learning to Evaluate Image CaptioningCode0
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention0
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition0
Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network0
Data augmentation instead of explicit regularizationCode0
Semantically Selective Augmentation for Deep Compact Person Re-Identification0
Transformationally Identical and Invariant Convolutional Neural Networks through Symmetric Element Operators0
A Systematic Evaluation of Recent Deep Learning Architectures for Fine-Grained Vehicle ClassificationCode0
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data0
Findings of the Second Workshop on Neural Machine Translation and Generation0
Speaker-Follower Models for Vision-and-Language NavigationCode0
Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples0
Training Augmentation with Adversarial Examples for Robust Speech Recognition0
EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signalsCode1
Study and development of a Computer-Aided Diagnosis system for classification of chest x-ray images using convolutional neural networks pre-trained for ImageNet and data augmentation0
Pose-Guided Photorealistic Face Rotation0
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion CompensationCode0
DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis0
Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System0
Lyb3b at SemEval-2018 Task 11: Machine Comprehension Task using Deep Learning Models0
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network0
Self-Training for Jointly Learning to Ask and Answer Questions0
Combining Pyramid Pooling and Attention Mechanism for Pelvic MR Image Semantic Segmentaion0
MONET: Multiview Semi-supervised Keypoint Detection via Epipolar DivergenceCode0
Accurate pedestrian localization in overhead depth images via Height-Augmented HOG0
Long-time predictive modeling of nonlinear dynamical systems using neural networks0
Why do deep convolutional networks generalize so poorly to small image transformations?Code1
Generalizing to Unseen Domains via Adversarial Data AugmentationCode0
Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks0
Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks0
Improved Mixed-Example Data AugmentationCode0
Transductive Label Augmentation for Improved Deep Network Learning0
Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation0
AutoAugment: Learning Augmentation Policies from DataCode3
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM0
Input and Weight Space Smoothing for Semi-supervised Learning0
Enriched Long-term Recurrent Convolutional Network for Facial Micro-Expression RecognitionCode0
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models0
Abstractive Text Classification Using Sequence-to-convolution Neural NetworksCode0
Counterexample-Guided Data AugmentationCode0
Feature Affinity based Pseudo Labeling for Semi-supervised Person Re-identification0
Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification0
Resisting Large Data Variations via Introspective Transformation Network0
Contextual Augmentation: Data Augmentation by Words with Paradigmatic RelationsCode0
Show:102550
← PrevPage 161 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 2×96d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified