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 74517500 of 8378 papers

TitleStatusHype
Data Augmentation for End-to-End Speech Translation: FBK@IWSLT ‘190
Multi-defect microscopy image restoration under limited data conditions0
Cross-Domain Face Synthesis using a Controllable GANCode0
Adapting Multilingual Neural Machine Translation to Unseen LanguagesCode0
Comprehensive Video Understanding: Video summarization with content-based video recommender design0
A CNN-based methodology for breast cancer diagnosis using thermal images0
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation0
Region-based Convolution Neural Network Approach for Accurate Segmentation of Pelvic Radiograph0
POIRot: A rotation invariant omni-directional pointnet0
Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions0
Neighborhood Watch: Representation Learning with Local-Margin Triplet Loss and Sampling Strategy for K-Nearest-Neighbor Image Classification0
Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network0
Superposition as Data Augmentation using LSTM and HMM in Small Training Sets0
Analyzing ASR pretraining for low-resource speech-to-text translation0
Occlusions for Effective Data Augmentation in Image Classification0
Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model0
Discriminative Neural Clustering for Speaker DiarisationCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
Good, Better, Best: Textual Distractors Generation for Multiple-Choice Visual Question Answering via Reinforcement Learning0
Boosting Mapping Functionality of Neural Networks via Latent Feature Generation based on Reversible Learning0
MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep LearningCode0
Cascaded Generation of High-quality Color Visible Face Images from Thermal Captures0
Label-efficient audio classification through multitask learning and self-supervision0
MonaLog: a Lightweight System for Natural Language Inference Based on MonotonicityCode0
Real-Time Lip Sync for Live 2D AnimationCode0
Towards More Sample Efficiency in Reinforcement Learning with Data AugmentationCode0
Illumination-Based Data Augmentation for Robust Background SubtractionCode0
Automatic Data Augmentation by Learning the Deterministic PolicyCode0
Anatomically-Informed Data Augmentation for functional MRI with Applications to Deep Learning0
ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness0
Self-supervised Label Augmentation via Input TransformationsCode0
Sketch-Specific Data Augmentation for Freehand Sketch Recognition0
Generative Image Translation for Data Augmentation in Colorectal Histopathology ImagesCode0
Cross-Domain Image Classification through Neural-Style Transfer Data AugmentationCode0
Adversarial Pulmonary Pathology Translation for Pairwise Chest X-ray Data AugmentationCode0
Efficient and Adaptive Kernelization for Nonlinear Max-margin Multi-view Learning0
Towards DeepSpray: Using Convolutional Neural Network to post-process Shadowgraphy Images of Liquid Atomization0
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement LearningCode0
Unconstrained Road Marking Recognition with Generative Adversarial Networks0
First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation0
A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification0
CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech0
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation0
Controlled Text Generation for Data Augmentation in Intelligent Artificial Agents0
Two Stream Networks for Self-Supervised Ego-Motion Estimation0
ANDA: A Novel Data Augmentation Technique Applied to Salient Object DetectionCode0
Partial differential equation regularization for supervised machine learning0
Cardiac Segmentation of LGE MRI with Noisy Labels0
Learning Dense Wide Baseline Stereo Matching for People0
Augmenting learning using symmetry in a biologically-inspired domain0
Show:102550
← PrevPage 150 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