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 1851–1900 of 8378 papers

TitleStatusHype
Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack—0
Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines—0
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive LearningCode1
Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation—0
EventRPG: Event Data Augmentation with Relevance Propagation GuidanceCode1
Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound ImagesCode0
Don't Judge by the Look: Towards Motion Coherent Video RepresentationCode0
7T MRI Synthesization from 3T AcquisitionsCode1
NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTICode0
Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods—0
Data Augmentation in Human-Centric Vision—0
VIGFace: Virtual Identity Generation for Privacy-Free Face RecognitionCode0
Can physical information aid the generalization ability of Neural Networks for hydraulic modeling?—0
IG-FIQA: Improving Face Image Quality Assessment through Intra-class Variance Guidance robust to Inaccurate Pseudo-LabelsCode0
Improved Image-based Pose Regressor Models for Underwater Environments—0
Boosting Disfluency Detection with Large Language Model as Disfluency GeneratorCode0
Reduced Jeffries-Matusita distance: A Novel Loss Function to Improve Generalization Performance of Deep Classification Models—0
METER: a mobile vision transformer architecture for monocular depth estimationCode0
Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization—0
Disentangling Policy from Offline Task Representation Learning via Adversarial Data AugmentationCode0
Dataset Condensation for Time Series Classification via Dual Domain MatchingCode1
Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models—0
Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource LanguagesCode1
Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation StrategiesCode0
Repeated Padding for Sequential RecommendationCode1
EarthLoc: Astronaut Photography Localization by Indexing Earth from SpaceCode2
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations—0
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization PerspectiveCode1
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack—0
SCORE: Self-supervised Correspondence Fine-tuning for Improved Content RepresentationsCode0
BSDA: Bayesian Random Semantic Data Augmentation for Medical Image ClassificationCode0
Large Language Models on Fine-grained Emotion Detection Dataset with Data Augmentation and Transfer Learning—0
MATRIX: Multi-Agent Trajectory Generation with Diverse Contexts—0
A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN—0
Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity—0
PIPsUS: Self-Supervised Dense Point Tracking in UltrasoundCode0
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via PromptsCode1
Improving the Successful Robotic Grasp Detection Using Convolutional Neural Networks—0
Control-based Graph Embeddings with Data Augmentation for Contrastive Learning—0
A data-centric approach to class-specific bias in image data augmentation—0
Delving into the Trajectory Long-tail Distribution for Muti-object TrackingCode2
Symmetry Considerations for Learning Task Symmetric Robot PoliciesCode7
Low-Resource Court Judgment Summarization for Common Law SystemsCode0
Generative Active Learning with Variational Autoencoder for Radiology Data Generation in Veterinary Medicine—0
MolNexTR: A Generalized Deep Learning Model for Molecular Image RecognitionCode2
Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and ApplicationsCode2
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsCode1
ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic SegmentationCode0
Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types—0
Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment—0
Show:102550
← PrevPage 38 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