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 4051–4100 of 8378 papers

TitleStatusHype
Robustness and invariance properties of image classifiers—0
Augraphy: A Data Augmentation Library for Document ImagesCode2
FAST-AID Brain: Fast and Accurate Segmentation Tool using Artificial Intelligence Developed for BrainCode0
A Diffusion Model Predicts 3D Shapes from 2D Microscopy ImagesCode1
Visual Speech Recognition in a Driver Assistance System—0
Synthetic Latent Fingerprint Generator—0
Effective Image Tampering Localization with Multi-Scale ConvNeXt Feature FusionCode0
Radial Prediction Domain Adaption Classifier for the MIDOG 2022 ChallengeCode0
Detection and Classification of Brain tumors Using Deep Convolutional Neural Networks—0
Bayesian Neural Network Language Modeling for Speech RecognitionCode0
Object Goal Navigation using Data Regularized Q-Learning—0
Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity—0
Leveraging Symmetrical Convolutional Transformer Networks for Speech to Singing Voice Style Transfer—0
Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge—0
Multi tasks RetinaNet for mitosis detection—0
Data Augmentation for Graph Data: Recent Advancements—0
Image augmentation improves few-shot classification performance in plant disease recognition—0
Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations—0
Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation—0
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity RecognitionCode1
SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-ResolutionCode1
A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)—0
Motion Robust High-Speed Light-Weighted Object Detection With Event CameraCode1
A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels—0
Data augmentation on graphs for table type classificationCode0
Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic SegmentationCode1
The Value of Out-of-Distribution DataCode1
Learning linear modules in a dynamic network with missing node observations—0
Unsupervised Question Answering via Answer DiversifyingCode0
Multimodal Crop Type Classification Fusing Multi-Spectral Satellite Time Series with Farmers Crop Rotations and Local Crop Distribution—0
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models—0
A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function PerspectiveCode1
Predicting the Masses of Exotic Hadrons with Data Augmentation Using Multilayer Perceptron—0
Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic DataCode1
MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue GenerationCode0
On the Privacy Effect of Data Enhancement via the Lens of MemorizationCode0
Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation—0
Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models—0
PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data AugmentationCode0
PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose EstimationCode1
Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of SuccessCode0
The Causal Structure of Domain Invariant Supervised Representation Learning—0
SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding—0
ARIEL: Adversarial Graph Contrastive LearningCode0
Online 3D Bin Packing Reinforcement Learning Solution with Buffer—0
Syntax-driven Data Augmentation for Named Entity RecognitionCode0
Gradient Mask: Lateral Inhibition Mechanism Improves Performance in Artificial Neural Networks—0
Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series ClassificationCode2
Enhancing Graph Contrastive Learning with Node Similarity—0
Show:102550
← PrevPage 82 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