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 7651–7700 of 8378 papers

TitleStatusHype
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes—0
Data Interpolating Prediction: Alternative Interpretation of Mixup—0
Efficient data augmentation using graph imputation neural networks—0
Predicting Confusion from Eye-Tracking Data with Recurrent Neural NetworksCode0
Generalizing Back-Translation in Neural Machine Translation—0
Can neural networks understand monotonicity reasoning?Code0
Learning to Ask Unanswerable Questions for Machine Reading Comprehension—0
CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training BudgetsCode0
Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis—0
Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise—0
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR—0
Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection—0
Warping Resilient Scalable Anomaly Detection in Time Series—0
Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation—0
Learning robust visual representations using data augmentation invarianceCode0
iProStruct2D: Identifying protein structural classes by deep learning via 2D representations—0
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology—0
Automatic brain tissue segmentation in fetal MRI using convolutional neural networks—0
Generalized Data Augmentation for Low-Resource Translation—0
An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD DistanceCode0
A Preliminary Study on Data Augmentation of Deep Learning for Image Classification—0
When Unseen Domain Generalization is Unnecessary? Rethinking Data AugmentationCode0
Bad Global Minima Exist and SGD Can Reach ThemCode0
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian AugmentationCode0
Practical Deep Learning with Bayesian PrinciplesCode0
Efficient, Lexicon-Free OCR using Deep Learning—0
Farm land weed detection with region-based deep convolutional neural networks—0
Selective Style Transfer for TextCode0
DualDis: Dual-Branch Disentangling with Adversarial LearningCode0
Achieving Generalizable Robustness of Deep Neural Networks by Stability Training—0
Topological AutoencodersCode0
Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain—0
Learning Representations by Maximizing Mutual Information Across ViewsCode0
Data Augmentation for Object Detection via Progressive and Selective Instance-SwitchingCode0
SINAI-DL at SemEval-2019 Task 5: Recurrent networks and data augmentation by paraphrasing—0
Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping—0
SSN-SPARKS at SemEval-2019 Task 9: Mining Suggestions from Online Reviews using Deep Learning Techniques on Augmented Data—0
Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification—0
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data AugmentationCode0
Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation—0
T\"upa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing—0
Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces—0
SolomonLab at SemEval-2019 Task 8: Question Factuality and Answer Veracity Prediction in Community Forums—0
Emad at SemEval-2019 Task 6: Offensive Language Identification using Traditional Machine Learning and Deep Learning approaches—0
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting—0
Catastrophic Child's Play: Easy to Perform, Hard to Defend Adversarial Attacks—0
Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding—0
Learning Pose Grammar for Monocular 3D Pose Estimation—0
SINAI-DL at SemEval-2019 Task 7: Data Augmentation and Temporal Expressions—0
Training Data Augmentation for Context-Sensitive Neural Lemmatizer Using Inflection Tables and Raw TextCode0
Show:102550
← PrevPage 154 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