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 5351–5400 of 8378 papers

TitleStatusHype
AAVAE: Augmentation-Augmented Variational Autoencoders—0
Theoretical Analysis of Consistency Regularization with Limited Augmented Data—0
Best Practices in Pool-based Active Learning for Image Classification—0
Autoregressive Latent Video Prediction with High-Fidelity Image Generator—0
SketchODE: Learning neural sketch representation in continuous time—0
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different—0
Neuro-Symbolic Ontology-Mediated Query Answering—0
Mistake-driven Image Classification with FastGAN and SpinalNet—0
Noisy Adversarial Training—0
Self-Supervised Learning of Motion-Informed Latents—0
CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation—0
Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning—0
Contrastive Learning is Just Meta-Learning—0
Learnability and Expressiveness in Self-Supervised Learning—0
Vicinal Counting Networks—0
Latent Feature Disentanglement For Visual Domain Generalization—0
Adaptive Unbiased Teacher for Cross-Domain Object Detection—0
Understanding the Success of Knowledge Distillation -- A Data Augmentation Perspective—0
Multi-Task Distribution Learning—0
Approximate Bijective Correspondence for isolating factors of variationCode0
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet TrainingCode1
DM-CT: Consistency Training with Data and Model Perturbation—0
SynCLR: A Synthesis Framework for Contrastive Learning of out-of-domain Speech Representations—0
AutoCoG: A Unified Data-Modal Co-Search Framework for Graph Neural Networks—0
CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization—0
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning—0
Where is the bottleneck in long-tailed classification?—0
Improving Discriminative Visual Representation Learning via Automatic Mixup—0
Stochastic Training is Not Necessary for GeneralizationCode1
Segmentation of Roads in Satellite Images using specially modified U-Net CNNs—0
Adaptive Multi-layer Contrastive Graph Neural Networks—0
Learning Background Invariance Improves Generalization and Robustness in Self-Supervised Learning on ImageNet and Beyond—0
Prediction of the Facial Growth Direction is Challenging—0
Layer-Parallel Training of Residual Networks with Auxiliary Variables—0
Optimized Automated Cardiac MR Scar Quantification with GAN-Based Data AugmentationCode0
A novel network training approach for open set image recognition—0
DAMix: A Density-Aware Mixup Augmentation for Single Image Dehazing under Domain Shift—0
Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationCode1
A real-time and high-precision method for small traffic-signs recognitionCode1
Unsupervised Cross-Modality Domain Adaptation for Segmenting Vestibular Schwannoma and Cochlea with Data Augmentation and Model Ensemble—0
SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation ExtractionCode1
GeomGCL: Geometric Graph Contrastive Learning for Molecular Property PredictionCode1
A Diversity-Enhanced and Constraints-Relaxed Augmentation for Low-Resource Classification—0
Faithful Target Attribute Prediction in Neural Machine TranslationCode0
Dense Contrastive Visual-Linguistic Pretraining—0
Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks—0
Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical OverlapCode0
Distiller: A Systematic Study of Model Distillation Methods in Natural Language Processing—0
ChannelAugment: Improving generalization of multi-channel ASR by training with input channel randomization—0
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge—0
Show:102550
← PrevPage 108 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