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 7001–7050 of 8378 papers

TitleStatusHype
EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision—0
EmoDiarize: Speaker Diarization and Emotion Identification from Speech Signals using Convolutional Neural Networks—0
EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection—0
Emotion Classification of Children Expressions—0
Emotion Detection from EEG using Transfer Learning—0
Emotion Selectable End-to-End Text-based Speech Editing—0
Empirical Evaluation of the Segment Anything Model (SAM) for Brain Tumor Segmentation—0
Empowering Large Language Models for Textual Data Augmentation—0
Enabling Tensor Decomposition for Time-Series Classification via A Simple Pseudo-Laplacian Contrast—0
Encoding Power Traces as Images for Efficient Side-Channel Analysis—0
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization—0
Endora: Video Generation Models as Endoscopy Simulators—0
End-to-End Action Segmentation Transformer—0
End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection—0
End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks—0
End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales—0
End to End Generative Meta Curriculum Learning For Medical Data Augmentation—0
End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth Data—0
End-to-end Neural Diarization: From Transformer to Conformer—0
End-to-end neural networks for subvocal speech recognition—0
End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning—0
End-to-end Recurrent Denoising Autoencoder Embeddings for Speaker Identification—0
End-to-End Speech Recognition with High-Frame-Rate Features Extraction—0
End-to-End Speech Translation of Arabic to English Broadcast News—0
End-to-end Speech Translation System Description of LIT for IWSLT 2019—0
End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020—0
end-to-end training of a large vocabulary end-to-end speech recognition system—0
Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations—0
English-Russian Data Augmentation for Neural Machine Translation—0
Enhanced Convolutional Neural Tangent Kernels—0
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation—0
Enhanced Few-Shot Class-Incremental Learning via Ensemble Models—0
Enhanced Generative Adversarial Networks for Unseen Word Generation from EEG Signals—0
Enhanced Image Classification With Data Augmentation Using Position Coordinates—0
Enhanced Image Reconstruction From Quarter Sampling Measurements Using An Adapted Very Deep Super Resolution Network—0
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics—0
Enhanced Offensive Language Detection Through Data Augmentation—0
Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks—0
Enhanced Transformer Model for Data-to-Text Generation—0
Enhancement of text recognition for hanja handwritten documents of Ancient Korea—0
EnhancePPG: Improving PPG-based Heart Rate Estimation with Self-Supervision and Augmentation—0
Enhance Visual Recognition under Adverse Conditions via Deep Networks—0
Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation—0
Enhancing Audio Augmentation Methods with Consistency Learning—0
Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation—0
Enhancing Breast Cancer Diagnosis in Mammography: Evaluation and Integration of Convolutional Neural Networks and Explainable AI—0
Understanding and Reducing the Class-Dependent Effects of Data Augmentation with A Two-Player Game Approach—0
Enhancing DeepLabV3+ to Fuse Aerial and Satellite Images for Semantic Segmentation—0
Enhancing Diffusion Models for High-Quality Image Generation—0
Enhancing DR Classification with Swin Transformer and Shifted Window Attention—0
Show:102550
← PrevPage 141 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