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

Showing 80518100 of 8378 papers

TitleStatusHype
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning0
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model0
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings0
Image Ordinal Classification and Understanding: Grid Dropout with Masking Label0
Deep JSLC: A Multimodal Corpus Collection for Data-driven Generation of Japanese Sign Language Expressions0
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models0
Simulating ASR errors for training SLU systems0
Augmenting Image Question Answering Dataset by Exploiting Image Captions0
Handling Rare Word Problem using Synthetic Training Data for Sinhala and Tamil Neural Machine Translation0
Generalizing Across Domains via Cross-Gradient TrainingCode0
Simulating dysarthric speech for training data augmentation in clinical speech applications0
Disentangling Factors of Variation with Cycle-Consistent Variational Auto-EncodersCode1
Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model0
Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data0
Learning to See the Invisible: End-to-End Trainable Amodal Instance SegmentationCode0
MVTec D2S: Densely Segmented Supermarket Dataset0
Word Embedding Perturbation for Sentence ClassificationCode0
Learning to Refine Human Pose Estimation0
ECG arrhythmia classification using a 2-D convolutional neural networkCode1
Gender Bias in Coreference Resolution: Evaluation and Debiasing MethodsCode1
Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages0
Robust Machine Comprehension Models via Adversarial Training0
Building robust prediction models for defective sensor data using Artificial Neural Networks0
Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing0
3D G-CNNs for Pulmonary Nodule Detection0
One Kernel to Solve Nearly Everything: Unified 3D Binary Convolutions for Image Analysis0
Real-world plant species identification based on deep convolutional neural networks and visual attention0
E-commerce Anomaly Detection: A Bayesian Semi-Supervised Tensor Decomposition Approach using Natural Gradients0
Roto-Translation Covariant Convolutional Networks for Medical Image AnalysisCode1
Detecting Multi-Oriented Text with Corner-based Region ProposalsCode1
On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networks0
EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field ImagesCode0
Impact of ultrasound image reconstruction method on breast lesion classification with neural transfer learning0
Semi-Supervised Deep Metrics for Image Registration0
Generative Adversarial Learning for Spectrum Sensing0
Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks0
Parallel Grid Pooling for Data AugmentationCode0
Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection0
Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation0
Multi-Modal Data Augmentation for End-to-End ASR0
BAGAN: Data Augmentation with Balancing GANCode1
Learning the Localization Function: Machine Learning Approach to Fingerprinting Localization0
Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks0
A Kernel Theory of Modern Data Augmentation0
Large Margin Deep Networks for ClassificationCode0
A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images0
Differential Expression Analysis of Dynamical Sequencing Count Data with a Gamma Markov Chain0
New Results on Multi-Step Traffic Flow Prediction0
GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification0
Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and AugmentationCode1
Show:102550
← PrevPage 162 of 168Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeiT-B (+MixPro)Accuracy (%)82.9Unverified
2ResNet-200 (DeepAA)Accuracy (%)81.32Unverified
3DeiT-S (+MixPro)Accuracy (%)81.3Unverified
4ResNet-200 (Fast AA)Accuracy (%)80.6Unverified
5ResNet-200 (UA)Accuracy (%)80.4Unverified
6ResNet-200 (AA)Accuracy (%)80Unverified
7ResNet-50 (DeepAA)Accuracy (%)78.3Unverified
8ResNet-50 (TA wide)Accuracy (%)78.07Unverified
9ResNet-50 (LoRot-E)Accuracy (%)77.72Unverified
10ResNet-50 (LoRot-I)Accuracy (%)77.71Unverified
#ModelMetricClaimedVerifiedStatus
1WideResNet-40-2 (Faster AA)Percentage error3.7Unverified
2Shake-Shake (26 2×32d) (Faster AA)Percentage error2.7Unverified
3WideResNet-28-10 (Faster AA)Percentage error2.6Unverified
4Shake-Shake (26 2×112d) (Faster AA)Percentage error2Unverified
5Shake-Shake (26 2×96d) (Faster AA)Percentage error2Unverified
#ModelMetricClaimedVerifiedStatus
1DiffAugClassification Accuracy92.7Unverified
2PaCMAPClassification Accuracy85.3Unverified
3hNNEClassification Accuracy77.4Unverified
4TopoAEClassification Accuracy74.6Unverified