Results 21 to 30 of about 598,648 (280)
Differentiable Automatic Data Augmentation [PDF]
, 2020 Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However, AutoAugment is extremely computationally expensive, limiting its wide applicability.
Li, Yonggang +5 more
openaire +4 more sources
Data augmentation and semi-supervised learning for deep neural networks-based text classifier [PDF]
, 2020 User feedback is essential for understanding user needs. In this paper, we use free-text obtained from a survey on sleep-related issues to build a deep neural networks-based text classifier.
Devlin Jacob +5 more
core +1 more source
Data augmentation with Mobius transformations
Machine Learning: Science and Technology, 2021 Abstract Data augmentation has led to substantial improvements in the performance and generalization of deep models, and remains a highly adaptable method to evolving model architectures and varying amounts of data—in particular, extremely scarce amounts of available training data.
Sharon Zhou +4 more
openaire +2 more sources
Hyperspectral Data Augmentation
CoRR, 2019 Submitted to IEEE Geoscience and Remote Sensing ...
Jakub Nalepa +2 more
openaire +2 more sources
On Data Augmentation for GAN Training [PDF]
IEEE Transactions on Image Processing, 2021 Accepted in IEEE Transactions on Image ...
Ngoc-Trung Tran +4 more
openaire +3 more sources
Spatio-Temporal Data Augmentation for Visual Surveillance
IEEE Access, 2021 Visual surveillance aims to detect a foreground object using a continuous image acquired from a fixed camera. Recent deep learning methods based on supervised learning show superior performance compared to classical background subtraction algorithms ...
Jae-Yeul Kim, Jong-Eun Ha
doaj +1 more source
CoRR, 2015 Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input space, thereby generating ...
Kishore Reddy Konda +3 more
openaire +2 more sources
Differentiable Data Augmentation with Kornia
CoRR, 2020 In this paper we present a review of the Kornia [1, 2] differentiable data augmentation (DDA) module for both for spatial (2D) and volumetric (3D) tensors. This module leverages differentiable computer vision solutions from Kornia, with an aim of integrating data augmentation (DA) pipelines and strategies to existing PyTorch components (e.g.
Shi, Jian +4 more
openaire +4 more sources
PENDUGAAN DATA HILANG DENGAN MENGGUNAKAN DATA AUGMENTATION
Media Statistika, 2011 Data augmentation is a method for estimating missing data. It is a special case of Gibbs sampling which has two important steps. The first step is imputation or I-step where the missing data is generated based on the conditional distributions for missing
Mesra Nova, Moch. Abdul Mukid
doaj +1 more source
Augmentation leak-prevention scheme using an auxiliary classifier in GAN-based image generation
Journal of King Saud University: Computer and Information Sciences, 2023 Although a generative adversarial network (GAN) can generate realistic and distinct images, it requires numerous training data. Data augmentation is a popular method of incrementing data using various augmentation operations.
Jonghwa Shim +3 more
doaj +1 more source