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 6301–6350 of 8378 papers

TitleStatusHype
Neural Machine Translation: A Review of Methods, Resources, and Tools—0
MRI brain tumor segmentation and uncertainty estimation using 3D-UNet architecturesCode1
Robustness Testing of Language Understanding in Task-Oriented DialogCode1
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention—0
Data augmentation and image understanding—0
Histogram Matching Augmentation for Domain Adaptation with Application to Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Image SegmentationCode1
Domain Generalisation with Domain Augmented Supervised Contrastive Learning (Student Abstract)—0
EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANsCode1
Self-supervised Pre-training with Hard Examples Improves Visual Representations—0
Adversarial Momentum-Contrastive Pre-TrainingCode0
Exploring Data Augmentation for Multi-Modality 3D Object DetectionCode1
Speech Synthesis as Augmentation for Low-Resource ASR—0
Automated Lay Language Summarization of Biomedical Scientific ReviewsCode0
MetaAugment: Sample-Aware Data Augmentation Policy Learning—0
Small-Footprint Wake Up Word Recognition in Noisy Environments Employing Competing-Words-Based Feature—0
Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning—0
ResizeMix: Mixing Data with Preserved Object Information and True Labels—0
Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems—0
Recent Advances of Generic Object Detection with Deep Learning: A Review—0
A pipeline for fair comparison of graph neural networks in node classification tasksCode1
Augmentation Inside the Network—0
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth EstimationCode1
Joint Search of Data Augmentation Policies and Network Architectures—0
SRoll3: A neural network approach to reduce large-scale systematic effects in the Planck High Frequency Instrument maps—0
Sparse Signal Models for Data Augmentation in Deep Learning ATRCode0
Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationCode1
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation—0
Copula-based synthetic data augmentation for machine-learning emulatorsCode1
Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting—0
Frozen-to-Paraffin: Categorization of Histological Frozen Sections by the Aid of Paraffin Sections and Generative Adversarial Networks—0
Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data AugmentationCode1
A Coarse-to-Fine Auto-Sampler For Long-tailed Image Recognition—0
Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation—0
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation—0
DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation—0
Biomechanical modelling of brain atrophy through deep learning—0
Simple Copy-Paste is a Strong Data Augmentation Method for Instance SegmentationCode1
C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot FillingCode1
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation—0
PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth ImageCode1
Multilingual Transfer Learning for QA Using Translation as Data Augmentation—0
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data—0
R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection—0
Generative Data Augmentation for Vehicle Detection in Aerial Images—0
Neural Rate Control for Video Encoding using Imitation Learning—0
Generative Adversarial Networks for Annotated Data Augmentation in Data Sparse NLU—0
MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias—0
Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text—0
Conditional Generation of Medical Images via Disentangled Adversarial Inference—0
VAE-Info-cGAN: Generating Synthetic Images by Combining Pixel-level and Feature-level Geospatial Conditional Inputs—0
Show:102550
← PrevPage 127 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