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 401–450 of 8378 papers

TitleStatusHype
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text GuidanceCode1
Adapting pretrained speech model for Mandarin lyrics transcription and alignmentCode1
CultureLLM: Incorporating Cultural Differences into Large Language ModelsCode1
A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augmentation TechniquesCode1
BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen VideosCode1
CVAE-GAN: Fine-Grained Image Generation through Asymmetric TrainingCode1
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution LayersCode1
Analysis of skin lesion images with deep learningCode1
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-LearningCode1
DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance ScalingCode1
DALE: Generative Data Augmentation for Low-Resource Legal NLPCode1
Data Augmentation Alone Can Improve Adversarial TrainingCode1
Boosted Neural Decoders: Achieving Extreme Reliability of LDPC Codes for 6G NetworksCode1
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell DataCode1
An Analysis of Simple Data Augmentation for Named Entity RecognitionCode1
Data Augmentation for Cross-Domain Named Entity RecognitionCode1
Data Augmentation for Deep Candlestick LearnerCode1
Data Augmentation for ElectrocardiogramsCode1
Data Augmentation for Graph Neural NetworksCode1
Data augmentation for learning predictive models on EEG: a systematic comparisonCode1
Data Augmentation for Low-Resource Neural Machine TranslationCode1
Bootstrap Your Object Detector via Mixed TrainingCode1
Data Augmentation for Spoken Language Understanding via Pretrained Language ModelsCode1
Data Augmentation-free Unsupervised Learning for 3D Point Cloud UnderstandingCode1
Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational AutoencoderCode1
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question UnderstandingCode1
Adaptive Graph Contrastive Learning for RecommendationCode1
Data Augmentation via Latent Diffusion for Saliency PredictionCode1
Data augmentation with Mobius transformationsCode1
BSUV-Net: A Fully-Convolutional Neural Network forBackground Subtraction of Unseen VideosCode1
Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment AnalysisCode1
Data-Free Knowledge Distillation via Feature Exchange and Activation Region ConstraintCode1
Alternate Diverse Teaching for Semi-supervised Medical Image SegmentationCode1
A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid EstimationCode1
Data Optimization in Deep Learning: A SurveyCode1
Data set creation and empirical analysis for detecting signs of depression from social media postingsCode1
Dataset Distillation via Curriculum Data Synthesis in Large Data EraCode1
Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image SegmentationCode1
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement LearningCode1
Exploring Discontinuity for Video Frame InterpolationCode1
BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature AnalysisCode1
Deep Convolutional Autoencoders for reconstructing magnetic resonance images of the healthy brainCode1
DeepCRF: Deep Learning-Enhanced CSI-Based RF Fingerprinting for Channel-Resilient WiFi Device IdentificationCode1
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust FinetuningCode1
Deep Entity Matching with Pre-Trained Language ModelsCode1
An Accurate Car Counting in Aerial Images Based on Convolutional Neural NetworksCode1
An augmentation strategy to mimic multi-scanner variability in MRICode1
AltFreezing for More General Video Face Forgery DetectionCode1
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
Show:102550
← PrevPage 9 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