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 5601–5625 of 8378 papers

TitleStatusHype
Training Keyword Spotting Models on Non-IID Data with Federated Learning—0
Training Language Models under Resource Constraints for Adversarial Advertisement Detection—0
Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization—0
Training Question Answering Models From Synthetic Data—0
Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping—0
Training Robust Spiking Neural Networks with ViewPoint Transform and SpatioTemporal Stretching—0
Training self-supervised peptide sequence models on artificially chopped proteins—0
Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection—0
Training Wake Word Detection with Synthesized Speech Data on Confusion Words—0
Training without training data: Improving the generalizability of automated medical abbreviation disambiguation—0
t-RAIN: Robust generalization under weather-aliasing label shift attacks—0
Trajectory-aware Principal Manifold Framework for Data Augmentation and Image Generation—0
TransAug: Translate as Augmentation for Sentence Embeddings—0
Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing—0
Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding—0
Transductive Label Augmentation for Improved Deep Network Learning—0
Transesophageal Echocardiography Generation using Anatomical Models—0
Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation—0
Transferable Unsupervised Robust Representation Learning—0
Transfer Incremental Learning using Data Augmentation—0
Transfer Learning and Augmentation for Word Sense Disambiguation—0
Transfer Learning and SpecAugment applied to SSVEP Based BCI Classification—0
Transfer Learning for Oral Cancer Detection using Microscopic Images—0
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping—0
Transfer Learning on Manifolds via Learned Transport Operators—0
Show:102550
← PrevPage 225 of 336Next →
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 2×96d) (Faster AA)Percentage error2—Unverified
5Shake-Shake (26 2×112d) (Faster AA)Percentage error2—Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7—Unverified
2PaCMAPClassification Accuracy85.3—Unverified
3hNNEClassification Accuracy77.4—Unverified
4TopoAEClassification Accuracy74.6—Unverified