Results 21 to 30 of about 252,636 (309)

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, Hu, Guosheng, Wang, Yongtao, Hospedales, Timothy, Robertson, Neil M., Yang, Yongxin   +5 more
openaire   +4 more sources

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, Jiequan Zhang, Hang Jiang, Torbjörn Lundh, Andrew Y. Ng   +4 more
openaire   +2 more sources

Hyperspectral Data Augmentation

CoRR, 2019
Submitted to IEEE Geoscience and Remote Sensing ...
Jakub Nalepa, Michal Myller, Michal Kawulok   +2 more
openaire   +2 more sources

Data augmentation approaches for polyp segmentation [PDF]

, 2022
openImage augmentation, and in general data augmentation techniques, can greatly improve the performances of deep neural networks through the creation of artificial patterns, in fact the presence of these new patterns helps the network to generalise thus
DORIZZA, ALBERTO
core  

fusion-jena/data-augmentation-ner-legal v1.0.0

, 2022
Source Code for Evaluating Data Augmentation for Named Entity Recognition over the German Legal ...
Erd, Robin, Feddoul, Leila
core   +1 more source

Text Data Augmentation Using Generative Adversarial Networks – A Systematic Review [PDF]

, 2023
Insufficient data is one of the main drawbacks in natural language processing tasks, and the most prevalent solution is to collect a decent amount of data that will be enough for the optimisation of the model.
Silva, Kanishka, Kanishka Silva, Kanishka Silva, Blain, Frederic; id_orcid, Can, Burcu, Sarwar, Raheem, Blain, Frederic, Mitkov, Ruslan   +6 more
core   +1 more source

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

data augmentation for chromosomes classification [PDF]

, 2023
openUtilizzo di diversi tipi di data augmentation per ottenere migliori prestazioni durante la classificazione di cromosomi con rete ...
GUGLIELMO, NICOLAS
core  

Dropout as data augmentation

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, Xavier Bouthillier, Roland Memisevic, Pascal Vincent   +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, Riba Pi, Edgar, Mishkin, Dmytro, Moreno-Noguer, Francesc, Nicolaou, Anguelos   +4 more
openaire   +4 more sources