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 4401–4450 of 8378 papers

TitleStatusHype
Self-supervised Learning for Label Sparsity in Computational Drug Repositioning—0
Towards Generalisable Audio Representations for Audio-Visual Navigation—0
Augmentation-Aware Self-Supervision for Data-Efficient GAN TrainingCode0
Learning Instance-Specific Augmentations by Capturing Local InvariancesCode1
A Kernelised Stein Statistic for Assessing Implicit Generative ModelsCode0
A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference—0
A Competitive Method for Dog Nose-print Re-identificationCode1
Voxel Field Fusion for 3D Object DetectionCode1
ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering SystemCode1
Adversarial synthesis based data-augmentation for code-switched spoken language identification—0
Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems—0
Segmentation Consistency Training: Out-of-Distribution Generalization for Medical Image SegmentationCode0
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech SynthesisCode2
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor EmbeddingCode0
GMML is All you NeedCode1
Easter2.0: Improving convolutional models for handwritten text recognitionCode1
Graph Structure Based Data Augmentation Method—0
A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks—0
Saliency Map Based Data Augmentation—0
MolScribe: Robust Molecular Structure Recognition with Image-To-Graph GenerationCode2
MDMLP: Image Classification from Scratch on Small Datasets with MLPCode0
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates—0
How Tempering Fixes Data Augmentation in Bayesian Neural Networks—0
Triangular Contrastive Learning on Molecular Graphs—0
Leveraging Causal Inference for Explainable Automatic Program Repair—0
Balancing Data through Data Augmentation Improves the Generality of Transfer Learning for Diabetic Retinopathy Classification—0
Audio Data Augmentation for Acoustic-to-articulatory Speech Inversion using Bidirectional Gated RNNs—0
Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation—0
Augmentation-induced Consistency Regularization for Classification—0
Leveraging QA Datasets to Improve Generative Data AugmentationCode0
Conditional set generation using Seq2seq models—0
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation—0
Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity TypingCode0
Counterfactual Data Augmentation improves Factuality of Abstractive Summarization—0
ReSmooth: Detecting and Utilizing OOD Samples when Training with Data AugmentationCode1
Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint—0
Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-trainingCode0
Robust 3D Object Detection in Cold Weather Conditions—0
Deep Learning-based automated classification of Chinese Speech Sound Disorders—0
EventMix: An Efficient Augmentation Strategy for Event-Based Data—0
Highly Accurate FMRI ADHD Classification using time distributed multi modal 3D CNNsCode1
One-Pixel Shortcut: on the Learning Preference of Deep Neural NetworksCode1
Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust ModelsCode0
Learning to Ignore Adversarial Attacks—0
QASem Parsing: Text-to-text Modeling of QA-based SemanticsCode1
Data augmentation for efficient learning from parametric experts—0
Sleep Posture One-Shot Learning Framework Using Kinematic Data Augmentation: In-Silico and In-Vivo Case Studies—0
CNNs Avoid Curse of Dimensionality by Learning on Patches—0
Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation—0
Producing Histopathology Phantom Images using Generative Adversarial Networks to improve Tumor Detection—0
Show:102550
← PrevPage 89 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