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
Self-Learning for Received Signal Strength Map Reconstruction with Neural Architecture Search—0
A Fusion-Denoising Attack on InstaHide with Data AugmentationCode0
Data Augmentation for Sign Language Gloss Translation—0
BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite ImagesCode1
Out-of-Manifold Regularization in Contextual Embedding Space for Text ClassificationCode1
Global Wheat Challenge 2020: Analysis of the competition design and winning models—0
Bootstrapping User and Item Representations for One-Class Collaborative Filtering—0
Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation—0
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge DistillationCode1
Label Geometry Aware Discriminator for Conditional Generative Networks—0
Cross-Modal Generative Augmentation for Visual Question Answering—0
Robust Training Using Natural Transformation—0
Multi-modal Conditional Bounding Box Regression for Music Score FollowingCode1
Examining and Mitigating Kernel Saturation in Convolutional Neural Networks using Negative Images—0
Truly shift-equivariant convolutional neural networks with adaptive polyphase upsamplingCode1
De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks—0
The Tags Are Alright: Robust Large-Scale RFID Clone Detection Through Federated Data-Augmented Radio Fingerprinting—0
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of TextCode1
Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs—0
A Survey of Data Augmentation Approaches for NLPCode2
ResMLP: Feedforward networks for image classification with data-efficient trainingCode1
Learning to Perturb Word Embeddings for Out-of-distribution QACode1
Handwritten Mathematical Expression Recognition with Bidirectionally Trained TransformerCode1
PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose EstimationCode1
Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance—0
Rethinking Ultrasound Augmentation: A Physics-Inspired Approach—0
PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex—0
R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation—0
Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution—0
Representation Learning for Clustering via Building ConsensusCode0
Consistency and Monotonicity Regularization for Neural Knowledge Tracing—0
AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning—0
Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational AutoencoderCode1
Self-supervised Augmentation Consistency for Adapting Semantic SegmentationCode1
Adapting Coreference Resolution for Processing Violent Death Narratives—0
Unsupervised data augmentation for object detection—0
TabAug: Data Driven Augmentation for Enhanced Table Structure RecognitionCode0
What Are Bayesian Neural Network Posteriors Really Like?Code1
Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation—0
Entailment as Few-Shot LearnerCode1
Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery—0
Improving BERT Model Using Contrastive Learning for Biomedical Relation ExtractionCode1
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization—0
NTIRE 2021 Depth Guided Image Relighting ChallengeCode1
Semi-supervised Interactive Intent Labeling—0
Towards Fair Federated Learning with Zero-Shot Data Augmentation—0
Machine Learning Algorithms for Breast Cancer Detection in Mammography Images: A Comparative Study—0
Semantic Data Augmentation for End-to-End Mandarin Speech Recognition—0
Accuracy Improvement for Fully Convolutional Networks via Selective Augmentation with Applications to Electrocardiogram Data—0
Automatic Diagnosis of COVID-19 from CT Images using CycleGAN and Transfer Learning—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