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 5901–5950 of 8378 papers

TitleStatusHype
Deep learning models for predicting RNA degradation via dual crowdsourcingCode0
LENS: Localization enhanced by NeRF synthesis—0
Fast Hand Detection in Collaborative Learning Environments—0
False Negative Distillation and Contrastive Learning for Personalized Outfit Recommendation—0
2D Multi-Class Model for Gray and White Matter Segmentation of the Cervical Spinal Cord at 7TCode0
Doubly-Trained Adversarial Data Augmentation for Neural Machine TranslationCode0
Investigation on Data Adaptation Techniques for Neural Named Entity Recognition—0
Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detectionCode0
Label-Occurrence-Balanced Mixup for Long-tailed Recognition—0
Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition—0
Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery—0
An evaluation of data augmentation methods for sound scene geotagging—0
Data Augmentation with Locally-time Reversed Speech for Automatic Speech Recognition—0
Distinguishing rule- and exemplar-based generalization in learning systemsCode0
Combining Image Features and Patient Metadata to Enhance Transfer Learning—0
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts—0
On the Surrogate Gap between Contrastive and Supervised LossesCode0
Spectral Bias in Practice: The Role of Function Frequency in Generalization—0
Contrastive Learning for Unsupervised Radar Place Recognition—0
Deep Subspace analysing for Semi-Supervised multi-label classification of Diabetic Foot Ulcer—0
Overcoming limited battery data challenges: A coupled neural network approach—0
Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training—0
Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems—0
Balanced Masked and Standard Face Recognition—0
Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models—0
Music Playlist Title Generation: A Machine-Translation Approach—0
Using Out-of-the-Box Frameworks for Contrastive Unpaired Image Translation for Vestibular Schwannoma and Cochlea Segmentation: An approach for the crossMoDA Challenge—0
Significance of Data Augmentation for Improving Cleft Lip and Palate Speech Recognition—0
Data centric approach to Chinese Medical Speech Recognition—0
A Preliminary Study on Environmental Sound Classification Leveraging Large-Scale Pretrained Model and Semi-Supervised Learning—0
3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges—0
Data Augmentation Technology for Dysarthria Assistive Systems—0
Document Image Layout Analysis via Explicit Edge Embedding Network—0
RCRNN-based Sound Event Detection System with Specific Speech Resolution—0
Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder—0
DAAS: Differentiable Architecture and Augmentation Policy Search—0
CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification ModelsCode0
Workflow Augmentation of Video Data for Event Recognition with Time-Sensitive Neural Networks—0
Adaptive Unbiased Teacher for Cross-Domain Object Detection—0
Mistake-driven Image Classification with FastGAN and SpinalNet—0
Vicinal Counting Networks—0
CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation—0
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different—0
Self-Supervised Learning of Motion-Informed Latents—0
Adaptive Multi-layer Contrastive Graph Neural Networks—0
Multi-Task Distribution Learning—0
Deep convolutional recurrent neural network for short-interval EEG motor imagery classification—0
AAVAE: Augmentation-Augmented Variational Autoencoders—0
AutoCoG: A Unified Data-Modal Co-Search Framework for Graph Neural Networks—0
Self-supervised Learning for Sequential Recommendation with Model Augmentation—0
Show:102550
← PrevPage 119 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