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 75017550 of 8378 papers

TitleStatusHype
Data Augmentation Based on Distributed Expressions in Text Classification Tasks0
AdaTransform: Adaptive Data Transformation0
Student Specialization in Deep ReLU Networks With Finite Width and Input Dimension0
On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints0
LIP: Learning Instance Propagation for Video Object Segmentation0
Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers0
Urban Sound Tagging using Convolutional Neural NetworksCode0
Automatically Learning Data Augmentation Policies for Dialogue TasksCode0
Explainable Deep Learning for Augmentation of sRNA Expression Profiles0
Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks0
Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs0
Learning the Difference that Makes a Difference with Counterfactually-Augmented DataCode0
A Hybrid Deep Learning Architecture for Leukemic B-lymphoblast Classification0
Breast Cancer Diagnosis with Transfer Learning and Global Pooling0
Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training0
Regularising Deep Networks with Deep Generative Models0
Speech Recognition with Augmented Synthesized Speech0
When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It0
Resizable Neural Networks0
Data Augmentation in Training CNNs: Injecting Noise to Images0
Adaptive Data Augmentation with Deep Parallel Generative Models0
Atalaya at TASS 2019: Data Augmentation and Robust Embeddings for Sentiment Analysis0
Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks0
On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints0
Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement LearningCode0
Technical report on Conversational Question Answering0
Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust PerformanceCode0
Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in ClutterCode0
Deep Multi-Facial patches Aggregation Network for Expression Classification from Face Images0
How to improve CNN-based 6-DoF camera pose estimation0
Handwritten Amharic Character Recognition Using a Convolutional Neural Network0
Adversarial Learning of General Transformations for Data Augmentation0
Context-Aware Image Matting for Simultaneous Foreground and Alpha EstimationCode0
Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos0
Triplet-Aware Scene Graph Embeddings0
Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data0
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation0
Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant0
Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity0
Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition0
Cardiac MRI Image Segmentation for Left Ventricle and Right Ventricle using Deep Learning0
Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled NetworksCode0
MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech0
Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks0
Bridging the domain gap in cross-lingual document classificationCode0
PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes0
Wasserstein Diffusion Tikhonov Regularization0
Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade0
Multilingual Graphemic Hybrid ASR with Massive Data Augmentation0
Hierarchical Scene Coordinate Classification and Regression for Visual Localization0
Show:102550
← PrevPage 151 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