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 5401–5450 of 8378 papers

TitleStatusHype
Adversarial AutoAugment—0
Adversarial Backdoor Defense in CLIP—0
Adversarial Bone Length Attack on Action Recognition—0
Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification—0
Adversarial cycle-consistent synthesis of cerebral microbleeds for data augmentation—0
Adversarial Data Augmentation for Disordered Speech Recognition—0
Adversarial Data Augmentation for Robust Speaker Verification—0
Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition—0
Adversarial Data Augmentation via Deformation Statistics—0
Adversarial Diversity and Hard Positive Generation—0
Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization—0
Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models—0
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training—0
Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise—0
Adversarial Learning for Neural PDE Solvers with Sparse Data—0
Adversarially Optimized Mixup for Robust Classification—0
Adversarial Policy Optimization in Deep Reinforcement Learning—0
Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization—0
Adversarial Robustness for Deep Learning-based Wildfire Prediction Models—0
Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records—0
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes—0
Adversarial Semantic Augmentation for Training Generative Adversarial Networks under Limited Data—0
Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning—0
Adversarial synthesis based data-augmentation for code-switched spoken language identification—0
Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification—0
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions—0
Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models—0
AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing—0
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification—0
AEGR: A simple approach to gradient reversal in autoencoders for network anomaly detection—0
AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models—0
Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks—0
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset—0
AFEN: Respiratory Disease Classification using Ensemble Learning—0
AFFACT - Alignment-Free Facial Attribute Classification Technique—0
Affine Disentangled GAN for Interpretable and Robust AV Perception—0
Affine-Invariant Robust Training—0
Affine transformation estimation improves visual self-supervised learning—0
Affinity and Diversity: Quantifying Mechanisms of Data Augmentation—0
A First Attempt at Unreliable News Detection in Swedish—0
A Flat Minima Perspective on Understanding Augmentations and Model Robustness—0
A Fourier Domain Feature Approach for Human Activity Recognition & Fall Detection—0
A Fourier Perspective on Model Robustness in Computer Vision—0
A Fourth Wave of Open Data? Exploring the Spectrum of Scenarios for Open Data and Generative AI—0
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation—0
A Framework for Supervised and Unsupervised Segmentation and Classification of Materials Microstructure Images—0
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data—0
AfriNames: Most ASR models "butcher" African Names—0
AFSC: Adaptive Fourier Space Compression for Anomaly Detection—0
Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery—0
Show:102550
← PrevPage 109 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