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 151–200 of 8378 papers

TitleStatusHype
BOP Challenge 2020 on 6D Object LocalizationCode2
BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data TrainingCode2
BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with TransformerCode2
Generative Adversarial Network in Medical Imaging: A ReviewCode2
GraphGPT: Graph Instruction Tuning for Large Language ModelsCode2
HSIGene: A Foundation Model For Hyperspectral Image GenerationCode2
CodeS: Towards Building Open-source Language Models for Text-to-SQLCode2
Decoupling Representation Learning from Reinforcement LearningCode2
EarthLoc: Astronaut Photography Localization by Indexing Earth from SpaceCode2
Large Language Models Can Learn Temporal ReasoningCode2
LibFewShot: A Comprehensive Library for Few-shot LearningCode2
LightGCL: Simple Yet Effective Graph Contrastive Learning for RecommendationCode2
Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease ClassificationCode2
MindBridge: A Cross-Subject Brain Decoding FrameworkCode2
MolNexTR: A Generalized Deep Learning Model for Molecular Image RecognitionCode2
A Survey of Data Augmentation Approaches for NLPCode2
Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing CluesCode2
Saturn: Sample-efficient Generative Molecular Design using Memory ManipulationCode2
A Survey on Data Augmentation in Large Model EraCode2
BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature AnalysisCode1
Analyzing Overfitting under Class Imbalance in Neural Networks for Image SegmentationCode1
Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment AnalysisCode1
Analysis of skin lesion images with deep learningCode1
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D DetectionCode1
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement LearningCode1
Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image SegmentationCode1
An Accurate Car Counting in Aerial Images Based on Convolutional Neural NetworksCode1
BEVDiffLoc: End-to-End LiDAR Global Localization in BEV View based on Diffusion ModelCode1
A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint ModelsCode1
3D Common Corruptions and Data AugmentationCode1
An Analysis of Simple Data Augmentation for Named Entity RecognitionCode1
Exploring Discontinuity for Video Frame InterpolationCode1
BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification ContextCode1
Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource LanguagesCode1
Better plain ViT baselines for ImageNet-1kCode1
BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite ImagesCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Behavior Injection: Preparing Language Models for Reinforcement LearningCode1
Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuningCode1
AltFreezing for More General Video Face Forgery DetectionCode1
Alternate Diverse Teaching for Semi-supervised Medical Image SegmentationCode1
Bayesian Adversarial Human Motion SynthesisCode1
AMR-DA: Data Augmentation by Abstract Meaning RepresentationCode1
A Locality-based Neural Solver for Optical Motion CaptureCode1
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural NetworksCode1
Bayesian inference for logistic models using Polya-Gamma latent variablesCode1
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust FinetuningCode1
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper CalibrationCode1
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution RobustnessCode1
A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid EstimationCode1
Show:102550
← PrevPage 4 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