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 4501–4550 of 8378 papers

TitleStatusHype
Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images—0
1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification TrackCode0
Switchable Lightweight Anti-symmetric Processing (SLAP) with CNN Outspeeds Data Augmentation by Smaller Sample -- Application in Gomoku Reinforcement Learning—0
Benchmarking Robustness in Neural Radiance Fields—0
Look Beyond Bias with Entropic Adversarial Data AugmentationCode0
Reservoir Prediction by Machine Learning Methods on The Well Data and Seismic Attributes for Complex Coastal Conditions—0
CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations—0
SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain—0
Image Data Augmentation Approaches: A Comprehensive Survey and Future directionsCode0
Multiclass Semantic Segmentation to Identify Anatomical Sub-Regions of Brain and Measure Neuronal Health in Parkinson's Disease—0
Mask-then-Fill: A Flexible and Effective Data Augmentation Framework for Event Extraction—0
Tackling Data Bias in Painting Classification with Style TransferCode0
TWR-MCAE: A Data Augmentation Method for Through-the-Wall Radar Human Motion Recognition—0
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language UnderstandingCode0
Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater VehiclesCode0
Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise—0
Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN—0
Fine-Grained Hard Negative Mining: Generalizing Mitosis Detection with a Fifth of the MIDOG 2022 Dataset—0
Gaussian Blur and Relative Edge ResponseCode0
Learning Invariance from Generated Variance for Unsupervised Person Re-identificationCode0
SIRL: Similarity-based Implicit Representation Learning—0
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action RecognitionCode0
Neural Radiance Field with LiDAR maps—0
Towards Better Robustness against Common Corruptions for Unsupervised Domain AdaptationCode0
Center-aware Adversarial Augmentation for Single Domain Generalization—0
Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator—0
Unsupervised Prompt Tuning for Text-Driven Object Detection—0
Robust Heterogeneous Federated Learning under Data CorruptionCode0
ObjectStitch: Object Compositing With Diffusion Model—0
BiasAdv: Bias-Adversarial Augmentation for Model Debiasing—0
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training—0
Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision—0
RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced CategoriesCode0
Vector Quantization With Self-Attention for Quality-Independent Representation Learning—0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One ClassifierCode0
MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation—0
Markov Game Video Augmentation for Action Segmentation—0
Tracking Passengers and Baggage Items using Multiple Overhead Cameras at Security CheckpointsCode0
Learning to mask: Towards generalized face forgery detection—0
SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering—0
Data Augmentation using Transformers and Similarity Measures for Improving Arabic Text Classification—0
Joint Engagement Classification using Video Augmentation Techniques for Multi-person Human-robot Interaction—0
Detection of Active Emergency Vehicles using Per-Frame CNNs and Output Smoothing—0
Knowledge-Guided Data-Centric AI in Healthcare: Progress, Shortcomings, and Future Directions—0
General GAN-generated image detection by data augmentation in fingerprint domain—0
Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral SimilaritiesCode0
Understanding and Improving Transfer Learning of Deep Models via Neural Collapse—0
Time to Market Reduction for Hydrogen Fuel Cell Stacks using Generative Adversarial Networks—0
HMM-based data augmentation for E2E systems for building conversational speech synthesis systems—0
Audio Denoising for Robust Audio Fingerprinting—0
Show:102550
← PrevPage 91 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