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 6251–6300 of 8378 papers

TitleStatusHype
Extracting Pasture Phenotype and Biomass Percentages using Weakly Supervised Multi-target Deep Learning on a Small Dataset—0
Octave Mix: Data augmentation using frequency decomposition for activity recognition—0
Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification—0
Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN—0
Environment Transfer for Distributed Systems—0
A Robust Illumination-Invariant Camera System for Agricultural Applications—0
Iterative weak/self-supervised classification framework for abnormal events detectionCode1
SDA: Improving Text Generation with Self Data Augmentation—0
Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks—0
Substructure Substitution: Structured Data Augmentation for NLP—0
GridMix: Strong regularization through local context mapping—0
Channel Augmented Joint Learning for Visible-Infrared RecognitionCode0
Continuous Copy-Paste for One-Stage Multi-Object Tracking and SegmentationCode1
Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive LearningCode1
Robust 2D/3D Vehicle Parsing in Arbitrary Camera Views for CVISCode0
THDA: Treasure Hunt Data Augmentation for Semantic Navigation—0
C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing—0
Pose Invariant Topological Memory for Visual Navigation—0
SemiHand: Semi-Supervised Hand Pose Estimation With Consistency—0
Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks—0
A Simple Feature Augmentation for Domain Generalization—0
CONTEMPLATING REAL-WORLDOBJECT RECOGNITION—0
Faster and Smarter AutoAugment: Augmentation Policy Search Based on Dynamic Data-Clustering—0
DiffAutoML: Differentiable Joint Optimization for Efficient End-to-End Automated Machine Learning—0
MODALS: Modality-agnostic Automated Data Augmentation in the Latent SpaceCode1
NOSE Augment: Fast and Effective Data Augmentation Without Searching—0
Logit As Auxiliary Weak-supervision for More Reliable and Accurate Prediction—0
Generalization and Stability of GANs: A theory and promise from data augmentation—0
Neural Networks Preserve Invertibility Across Iterations: A Possible Source of Implicit Data Augmentation—0
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP—0
Redefining Self-Normalization Property—0
Recurrent Neural Network Architecture based on Dynamic Systems Theory for Data Driven Modelling of Complex Physical Systems—0
DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness—0
Tradeoffs in Data Augmentation: An Empirical Study—0
On the Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations—0
Switching-Aligned-Words Data Augmentation for Neural Machine Translation—0
Disentangling style and content for low resource video domain adaptation: a case study on keystroke inference attacks—0
Transferable Unsupervised Robust Representation Learning—0
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration—0
PriorityCut: Occlusion-aware Regularization for Image Animation—0
A Rigorous Evaluation of Real-World Distribution Shifts—0
The Importance of Importance Sampling for Deep Budgeted Training—0
Driving through the Lens: Improving Generalization of Learning-based Steering using Simulated Adversarial Examples—0
Data augmentation for deep learning based accelerated MRI reconstruction—0
What are effective labels for augmented data? Improving robustness with AutoLabel—0
Cut out the annotator, keep the cutout: better segmentation with weak supervision—0
Improving Generalizability of Protein Sequence Models via Data Augmentations—0
ROMUL: Scale Adaptative Population Based Training—0
FastIF: Scalable Influence Functions for Efficient Model Interpretation and DebuggingCode0
Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuningCode1
Show:102550
← PrevPage 126 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