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 3451–3500 of 8378 papers

TitleStatusHype
Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection—0
BloomVQA: Assessing Hierarchical Multi-modal Comprehension—0
Robust Machine Learning by Transforming and Augmenting Imperfect Training Data—0
Classification of complex local environments in systems of particle shapes through shape-symmetry encoded data augmentation—0
Leveraged Mel spectrograms using Harmonic and Percussive Components in Speech Emotion RecognitionCode0
The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data AugmentationsCode0
A Multimodal Approach for Advanced Pest Detection and Classification—0
COPD-FlowNet: Elevating Non-invasive COPD Diagnosis with CFD Simulations—0
PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields—0
Analisis Eksploratif Dan Augmentasi Data NSL-KDD Menggunakan Deep Generative Adversarial Networks Untuk Meningkatkan Performa Algoritma Extreme Gradient Boosting Dalam Klasifikasi Jenis Serangan Siber—0
Debiasing Multimodal Sarcasm Detection with Contrastive Learning—0
T-MAE: Temporal Masked Autoencoders for Point Cloud Representation LearningCode0
Small Dataset, Big Gains: Enhancing Reinforcement Learning by Offline Pre-Training with Model Based Augmentation—0
A Novel Dataset for Financial Education Text Simplification in Spanish—0
Multi-Microphone Noise Data Augmentation for DNN-based Own Voice Reconstruction for Hearables in Noisy Environments—0
Towards Automatic Data Augmentation for Disordered Speech Recognition—0
ComOM at VLSP 2023: A Dual-Stage Framework with BERTology and Unified Multi-Task Instruction Tuning Model for Vietnamese Comparative Opinion Mining—0
Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language InferenceCode0
TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-trainingCode0
PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition—0
Causal Optimal Transport of AbstractionsCode0
Semantic-aware Data Augmentation for Text-to-image SynthesisCode0
On the notion of Hallucinations from the lens of Bias and Validity in Synthetic CXR Images—0
Transferring Modality-Aware Pedestrian Attentive Learning for Visible-Infrared Person Re-identification—0
Creating Spoken Dialog Systems in Ultra-Low Resourced Settings—0
Semantic Image Synthesis for Abdominal CT—0
Improving age prediction: Utilizing LSTM-based dynamic forecasting for data augmentation in multivariate time series analysis—0
SqueezeSAM: User friendly mobile interactive segmentation—0
BoschAI @ Causal News Corpus 2023: Robust Cause-Effect Span Extraction using Multi-Layer Sequence Tagging and Data AugmentationCode0
Deep Imbalanced Learning for Multimodal Emotion Recognition in Conversations—0
Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input—0
Speech and Text-Based Emotion Recognizer—0
Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation—0
Temporal Supervised Contrastive Learning for Modeling Patient Risk ProgressionCode0
Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models—0
Image Synthesis-based Late Stage Cancer Augmentation and Semi-Supervised Segmentation for MRI Rectal Cancer Staging—0
Understanding Community Bias Amplification in Graph Representation Learning—0
Synthesizing Traffic Datasets using Graph Neural NetworksCode0
A Review On Table Recognition Based On Deep LearningCode0
HandDiffuse: Generative Controllers for Two-Hand Interactions via Diffusion Models—0
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation—0
Data Scarcity in Recommendation Systems: A Survey—0
Stable Diffusion for Data Augmentation in COCO and Weed Datasets—0
A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems—0
Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation—0
OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization—0
SurfaceAug: Closing the Gap in Multimodal Ground Truth Sampling—0
Indirect Gradient Matching for Adversarial Robust Distillation—0
XAIQA: Explainer-Based Data Augmentation for Extractive Question Answering—0
FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space—0
Show:102550
← PrevPage 70 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