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 1651–1700 of 8378 papers

TitleStatusHype
Time Series Data Augmentation as an Imbalanced Learning ProblemCode0
Hide and Seek: How Does Watermarking Impact Face Recognition?—0
Human-in-the-Loop Synthetic Text Data Inspection with Provenance TrackingCode0
Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition—0
Exploring the Robustness of In-Context Learning with Noisy LabelsCode0
Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin—0
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization—0
LLMs for Generating and Evaluating Counterfactuals: A Comprehensive StudyCode0
Empowering Large Language Models for Textual Data Augmentation—0
CSCO: Connectivity Search of Convolutional OperatorsCode0
Online Data Augmentation for Forecasting with Deep LearningCode0
CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint MatchingCode0
DE-CGAN: Boosting rTMS Treatment Prediction with Diversity Enhancing Conditional Generative Adversarial Networks—0
Asking and Answering Questions to Extract Event-Argument StructuresCode0
AAPL: Adding Attributes to Prompt Learning for Vision-Language ModelsCode1
SynCellFactory: Generative Data Augmentation for Cell Tracking—0
Boosting Model Resilience via Implicit Adversarial Data Augmentation—0
Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution—0
One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns—0
Neural Proto-Language Reconstruction—0
An Empirical Study of Aegis—0
EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification—0
Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking—0
A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data—0
SI-FID: Only One Objective Indicator for Evaluating Stitched Images—0
A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation—0
DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization—0
UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice QuestionsCode0
TopoLedgerBERT: Topological Learning of Ledger Description Embeddings using Siamese BERT-Networks—0
Unlocking Robust Segmentation Across All Age Groups via Continual Learning—0
Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoders—0
SOS-1K: A Fine-grained Suicide Risk Classification Dataset for Chinese Social Media AnalysisCode0
Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning—0
A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasksCode0
Aligning Actions and Walking to LLM-Generated Textual DescriptionsCode0
MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye trackingCode1
Guided Discrete Diffusion for Electronic Health Record Generation—0
Consistency Training by Synthetic Question Generation for Conversational Question AnsweringCode0
CORE: Data Augmentation for Link Prediction via Information Bottleneck—0
Simple In-place Data Augmentation for Surveillance Object Detection—0
D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes—0
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned DataCode1
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis—0
Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured—0
Exploring Augmentation and Cognitive Strategies for AI based Synthetic Personae—0
Offline Trajectory Generalization for Offline Reinforcement Learning—0
Clustering and Data Augmentation to Improve Accuracy of Sleep Assessment and Sleep Individuality Analysis—0
Classification of Prostate Cancer in 3D Magnetic Resonance Imaging Data based on Convolutional Neural Networks—0
Awareness of uncertainty in classification using a multivariate model and multi-views—0
Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms—0
Show:102550
← PrevPage 34 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