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 6626–6650 of 8378 papers

TitleStatusHype
What are effective labels for augmented data? Improving robustness with AutoLabel—0
Neural Networks Preserve Invertibility Across Iterations: A Possible Source of Implicit Data Augmentation—0
Logit As Auxiliary Weak-supervision for More Reliable and Accurate Prediction—0
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration—0
C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-Balancing—0
CONTEMPLATING REAL-WORLDOBJECT RECOGNITION—0
ROMUL: Scale Adaptative Population Based Training—0
Tradeoffs in Data Augmentation: An Empirical Study—0
THDA: Treasure Hunt Data Augmentation for Semantic Navigation—0
On the Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations—0
Recurrent Neural Network Architecture based on Dynamic Systems Theory for Data Driven Modelling of Complex Physical Systems—0
Transferable Unsupervised Robust Representation Learning—0
Robust 2D/3D Vehicle Parsing in Arbitrary Camera Views for CVISCode0
Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks—0
XLA: A Robust Unsupervised Data Augmentation Framework for Cross-Lingual NLP—0
DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness—0
Cut out the annotator, keep the cutout: better segmentation with weak supervision—0
SemiHand: Semi-Supervised Hand Pose Estimation With Consistency—0
Pose Invariant Topological Memory for Visual Navigation—0
Redefining Self-Normalization Property—0
Disentangling style and content for low resource video domain adaptation: a case study on keystroke inference attacks—0
Data augmentation for deep learning based accelerated MRI reconstruction—0
The Importance of Importance Sampling for Deep Budgeted Training—0
Generalization and Stability of GANs: A theory and promise from data augmentation—0
GridMix: Strong regularization through local context mapping—0
Show:102550
← PrevPage 266 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 2×112d) (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