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 6701–6750 of 8378 papers

TitleStatusHype
One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns—0
One-sample Guided Object Representation Disassembling—0
One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation—0
One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes—0
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models—0
On gradient descent training under data augmentation with on-line noisy copies—0
ColorSense: A Study on Color Vision in Machine Visual Recognition—0
On Improving an Already Competitive Segmentation Algorithm for the Cell Tracking Challenge - Lessons Learned—0
On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks—0
On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints—0
On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints—0
Online 3D Bin Packing Reinforcement Learning Solution with Buffer—0
Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark—0
On Linear Separation Capacity of Self-Supervised Representation Learning—0
Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation—0
Mixed Sample Augmentation for Online Distillation—0
On-line Recognition of Handwritten Mathematical Symbols—0
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration—0
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses—0
On Neural Inertial Classification Networks for Pedestrian Activity Recognition—0
On Nondeterminism and Instability in Optimizing Neural Networks—0
On regularization of gradient descent, layer imbalance and flat minima—0
On Robust Incremental Learning over Many Multilingual Steps—0
On Robustness of Neural Semantic Parsers—0
On Target Segmentation for Direct Speech Translation—0
On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation—0
On the Benefits of Invariance in Neural Networks—0
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency—0
On the Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations—0
An Empirical Study and Analysis on Open-Set Semi-Supervised Learning—0
On the effectiveness of convolutional autoencoders on image-based personalized recommender systems—0
On the effectiveness of GAN generated cardiac MRIs for segmentation—0
On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech—0
On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations—0
On the Effects of Knowledge-Augmented Data in Word Embeddings—0
On the Fairness of Generative Adversarial Networks (GANs)—0
On the Generalization Effects of DenseNet Model Structures—0
On the Impact of Data Augmentation on Downstream Performance in Natural Language Processing—0
On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''—0
On the Impact of Voice Anonymization on Speech Diagnostic Applications: a Case Study on COVID-19 Detection—0
On the Implicit Bias of Linear Equivariant Steerable Networks—0
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning—0
On the Importance of Visual Context for Data Augmentation in Scene Understanding—0
On the Language Coverage Bias for Neural Machine Translation—0
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?—0
On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning—0
On the Multidimensional Augmentation of Fingerprint Data for Indoor Localization in A Large-Scale Building Complex Based on Multi-Output Gaussian Process—0
On the notion of Hallucinations from the lens of Bias and Validity in Synthetic CXR Images—0
Understanding Robust Overfitting from the Feature Generalization Perspective—0
On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective—0
Show:102550
← PrevPage 135 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