A full stage data augmentation method in deep convolutional neural network for natural image classification

DOI10.1155/2020/4706576MaRDI QIDQ779087zbMATH OpenOpenAlexWikidataFDO

Authors Qinghe Zheng, Mingqiang Yang, Xinyu Tian, Nan Jiang, De-Qiang Wang

Publication date 21 July 2020

Published in Discrete Dynamics in Nature and Society (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1155/2020/4706576

zbMATH Keywords

computer visioninformation transfermodel ensemble

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Recommendations

• Seeking efficient data augmentation schemes via conditional and marginal augmentation
• Image augmentation with conformal mappings for a convolutional neural network
• Self-augmentation: generalizing deep networks to unseen classes for few-shot learning
• Asymptotically Exact Data Augmentation: Models, Properties, and Algorithms
• A theoretical comparison of the data augmentation, marginal augmentation and PX-DA algorithms

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning
• Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition
• Spatio-temporal convolution kernels

Cited in

(13)

• Bipartite multi-tracking in MASs with intermittent communication
• Salient slices: improved neural network training and performance with image entropy
• Convolutional neural network training strategy using knowledge transfer
• Influence of image data set noise on classification with a convolutional network
• Generative adversarial network based data augmentation to improve cervical cell classification model
• Visual attentional-driven deep learning method for flower recognition
• Fast mesh data augmentation via Chebyshev polynomial of spectral filtering
• The image caption method based on CNN-RNN deep learning and its optimization
• Convolutional neural network learning for generic data classification
• Optimization of deep convolutional neural network for large scale image classification
• Classification of Gaussian spatio-temporal data with stationary separable covariances
• Image augmentation with conformal mappings for a convolutional neural network
• An implicit memory-based method for supervised pattern recognition

Describes a project that uses

Uses Software

• CIFAR
• ImageNet
• AlexNet
• DnCNN

This page was built for publication: A full stage data augmentation method in deep convolutional neural network for natural image classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q779087)