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 4001–4050 of 8378 papers

TitleStatusHype
An Empirical Study of Automatic Post-Editing—0
KaliCalib: A Framework for Basketball Court Registration—0
Automatic Tooth Segmentation from 3D Dental Model using Deep Learning: A Quantitative Analysis of what can be learnt from a Single 3D Dental ModelCode0
One-Shot Synthesis of Images and Segmentation MasksCode1
HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator—0
A Light Recipe to Train Robust Vision TransformersCode1
On-Device Domain GeneralizationCode2
Non-Parallel Voice Conversion for ASR Augmentation—0
DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation—0
vec2text with Round-Trip Translations—0
Graph Contrastive Learning with Personalized Augmentation—0
Class-Level Logit PerturbationCode0
Predicting Brain Multigraph Population From a Single Graph Template for Boosting One-Shot ClassificationCode0
Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes—0
Hyperbolic Self-supervised Contrastive Learning Based Network Anomaly Detection—0
Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation—0
DoubleMix: Simple Interpolation-Based Data Augmentation for Text ClassificationCode1
Bias Challenges in Counterfactual Data Augmentation—0
Unified State Representation Learning under Data AugmentationCode0
Improving Keyphrase Extraction with Data Augmentation and Information Filtering—0
Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower SpeciesCode0
Anticipating the Unseen Discrepancy for Vision and Language Navigation—0
Ranking-Enhanced Unsupervised Sentence Representation LearningCode1
Saliency-based Multiple Region of Interest Detection from a Single 360° image—0
Video Vision Transformers for Violence Detection—0
The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagery—0
Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding—0
Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation—0
Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection—0
Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation ChainsCode1
Bayesian Mixed-Frequency Quantile Vector Autoregression: Eliciting tail risks of Monthly US GDP—0
A Deep Neural Network for Multiclass Bridge Element Parsing in Inspection Image Analysis—0
Time-domain speech super-resolution with GAN based modeling for telephony speaker verification—0
Selective Text Augmentation with Word Roles for Low-Resource Text ClassificationCode0
Training Strategies for Improved Lip-readingCode2
Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglement—0
Improving Compositional Generalization in Math Word Problem SolvingCode0
Back-to-Bones: Rediscovering the Role of Backbones in Domain GeneralizationCode0
LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile DevicesCode1
Random Text Perturbations Work, but not AlwaysCode0
Improving Translation of Out Of Vocabulary Words using Bilingual Lexicon Induction in Low-Resource Machine Translation—0
English-Russian Data Augmentation for Neural Machine Translation—0
Data Augmentation for Intent Classification of German Conversational Agents in the Finance Domain—0
Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances—0
Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax—0
XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation—0
Style-Agnostic Reinforcement LearningCode1
Generating Intermediate Steps for NLI with Next-Step Supervision—0
Feature Alignment by Uncertainty and Self-Training for Source-Free Unsupervised Domain Adaptation—0
EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud ComputingCode1
Show:102550
← PrevPage 81 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