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 5176–5200 of 8378 papers

TitleStatusHype
Your Image is Secretly the Last Frame of a Pseudo Video—0
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training—0
YuruGAN: Yuru-Chara Mascot Generator Using Generative Adversarial Networks With Clustering Small Dataset—0
Zero-pronoun Data Augmentation for Japanese-to-English Translation—0
ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPT—0
Zero-shot domain adaptation based on dual-level mix and contrast—0
Zero-Shot Generalization of Vision-Based RL Without Data Augmentation—0
Synthetic flow-based cryptomining attack generation through Generative Adversarial Networks—0
State Classification of Cooking Objects Using a VGG CNN—0
Two-Stage Convolutional Neural Network Architecture for Lung Nodule Detection—0
ROI Regularization for Semi-supervised and Supervised Learning—0
Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping—0
Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain—0
Achieving Generalizable Robustness of Deep Neural Networks by Stability Training—0
Dialog State Tracking with Reinforced Data Augmentation—0
Adversarial Learning of General Transformations for Data Augmentation—0
Deep Multi-Facial patches Aggregation Network for Expression Classification from Face Images—0
How to improve CNN-based 6-DoF camera pose estimation—0
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation—0
1-D Residual Convolutional Neural Network coupled with Data Augmentation and Regularization for the ICPHM 2023 Data Challenge—0
VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections—0
Trainable Pointwise Decoder Module for Point Cloud Segmentation—0
Label Augmentation for Neural Networks Robustness—0
RCDM: Enabling Robustness for Conditional Diffusion Model—0
Diverse Generation while Maintaining Semantic Coordination: A Diffusion-Based Data Augmentation Method for Object Detection—0
Show:102550
← PrevPage 208 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