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 5501–5550 of 8378 papers

TitleStatusHype
Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations—0
Plumeria at SemEval-2022 Task 6: Robust Approaches for Sarcasm Detection for English and Arabic Using Transformers and Data AugmentationCode0
Data augmentation with mixtures of max-entropy transformations for filling-level classification—0
Regularising for invariance to data augmentation improves supervised learning—0
Non-equilibrium molecular geometries in graph neural networks—0
An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions—0
A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification—0
Exploration of Various Deep Learning Models for Increased Accuracy in Automatic Polyp Detection—0
The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge—0
Robustness and Adaptation to Hidden Factors of Variation—0
Intelligent Crack Detection and Quantification in the Concrete Bridge: A Deep Learning-Assisted Image Processing Approach—0
Data Augmentation as Feature Manipulation—0
Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings—0
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from ImagesCode0
Enhanced Image Reconstruction From Quarter Sampling Measurements Using An Adapted Very Deep Super Resolution Network—0
A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge—0
Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information—0
Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data—0
Robots Autonomously Detecting People: A Multimodal Deep Contrastive Learning Method Robust to Intraclass Variations—0
Background Mixup Data Augmentation for Hand and Object-in-Contact Detection—0
Towards A Device-Independent Deep Learning Approach for the Automated Segmentation of Sonographic Fetal Brain Structures: A Multi-Center and Multi-Device Validation—0
Interactive Machine Learning for Image Captioning—0
Using Multi-scale SwinTransformer-HTC with Data augmentation in CoNIC Challenge—0
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language GenerationCode0
An Improved Deep Learning Approach For Product Recognition on Racks in Retail Stores—0
Automated Data Augmentations for Graph Classification—0
OptGAN: Optimizing and Interpreting the Latent Space of the Conditional Text-to-Image GANs—0
Identifying charge density and dielectric environment of graphene using Raman spectroscopy and deep learning—0
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration—0
Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning—0
Sample Efficiency of Data Augmentation Consistency Regularization—0
Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild—0
Improving Systematic Generalization Through Modularity and AugmentationCode0
Contrastive-mixup learning for improved speaker verification—0
Generating Synthetic Mobility Networks with Generative Adversarial Networks—0
A new data augmentation method for intent classification enhancement and its application on spoken conversation datasets—0
Spanish and English Phoneme Recognition by Training on Simulated Classroom Audio Recordings of Collaborative Learning EnvironmentsCode0
CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator—0
Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users—0
NetSentry: A Deep Learning Approach to Detecting Incipient Large-scale Network Attacks—0
Numeric Encoding Options with AutomungeCode0
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects—0
Gaussian and Non-Gaussian Universality of Data AugmentationCode0
Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models—0
Meta Knowledge Distillation—0
A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments—0
Beyond Deterministic Translation for Unsupervised Domain AdaptationCode0
Multi-style Training for South African Call Centre Audio—0
A Theory of PAC Learnability under Transformation Invariances—0
Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection—0
Show:102550
← PrevPage 111 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