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 6501–6550 of 8378 papers

TitleStatusHype
Multiclass Semantic Segmentation to Identify Anatomical Sub-Regions of Brain and Measure Neuronal Health in Parkinson's Disease—0
Multi-class Skin Cancer Classification Architecture Based on Deep Convolutional Neural Network—0
Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation—0
Multi-defect microscopy image restoration under limited data conditions—0
Multi-Domain Transformer-Based Counterfactual Augmentation for Earnings Call Analysis—0
MultiEarth 2023 Deforestation Challenge -- Team FOREVER—0
Multi-Epoch Learning for Deep Click-Through Rate Prediction Models—0
Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction—0
Multigrid-augmented deep learning preconditioners for the Helmholtz equation—0
Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection—0
Multi-hop Federated Private Data Augmentation with Sample Compression—0
Multilevel Context Representation for Improving Object Recognition—0
Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence—0
Multilingual Graphemic Hybrid ASR with Massive Data Augmentation—0
Multilingual Neural Machine Translation involving Indian Languages—0
Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021—0
Multilingual Speech Translation with Unified Transformer: Huawei Noah’s Ark Lab at IWSLT 2021—0
Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling—0
Multilingual Transfer Learning for QA Using Translation as Data Augmentation—0
MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations—0
Multi-Microphone Noise Data Augmentation for DNN-based Own Voice Reconstruction for Hearables in Noisy Environments—0
UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP—0
Multimodal Crop Type Classification Fusing Multi-Spectral Satellite Time Series with Farmers Crop Rotations and Local Crop Distribution—0
Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion—0
Multi-Modal Data Augmentation for End-to-End ASR—0
Multi-modal data generation with a deep metric variational autoencoder—0
Multimodal Dialogue State Tracking By QA Approach with Data Augmentation—0
Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models—0
Multi-Modality Microscopy Image Style Transfer for Nuclei Segmentation—0
Multimodal Physiological Signals Representation Learning via Multiscale Contrasting for Depression Recognition—0
Multi-Modal Representation Learning with Text-Driven Soft Masks—0
Multimodal Self-Supervised Learning for Medical Image Analysis—0
Multimodal Semi-supervised Learning Framework for Punctuation Prediction in Conversational Speech—0
Multi-object Tracking with Neural Gating Using Bilinear LSTM—0
Multi-Output Gaussian Process-Based Data Augmentation for Multi-Building and Multi-Floor Indoor Localization—0
Multi-Path Learnable Wavelet Neural Network for Image Classification—0
Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection—0
Multiple Instance Learning Convolutional Neural Networks for Object Recognition—0
Multiple Instance Learning for Brain Tumor Detection from Magnetic Resonance Spectroscopy Data—0
Multi-Resolution Fusion for Fully Automatic Cephalometric Landmark Detection—0
Multi-Sample ζ-mixup: Richer, More Realistic Synthetic Samples from a p-Series Interpolant—0
Multi-Scale and Multi-Direction GAN for CNN-Based Single Palm-V ein Identification—0
Multi-Scale Contrastive Learning for Video Temporal Grounding—0
Multi-Scales Data Augmentation Approach In Natural Language Inference For Artifacts Mitigation And Pre-Trained Model Optimization—0
Multi-Source Neural Machine Translation with Data Augmentation—0
Multi-Spectral Image Classification with Ultra-Lean Complex-Valued Models—0
Multispectral Object Detection with Deep Learning—0
Multistage Adversarial Losses for Pose-Based Human Image Synthesis—0
Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval—0
Multi-stream Attention-based BLSTM with Feature Segmentation for Speech Emotion Recognition—0
Show:102550
← PrevPage 131 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