• Home
  • Search
  • A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks
  • Open Access IconOpen Access
  • https://doi.org/10.1109/ijcnn55064.2022.9892528Copy DOI Icon

A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks

  • Jul 18, 2022
  • Binyan Hu +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Deep neural networks (DNNs) often rely on massive labelled data for training, which is inaccessible in many applications. Data augmentation (DA) tackles data scarcity by creating new labelled data from available ones. Different DA methods have different mechanisms and therefore using their generated labelled data for DNN training may help improving DNN's generalisation to different degrees. Combining multiple DA methods, namely multi-DA, for DNN training, provides a way to further boost generalisation. Among existing multi-DA based DNN training methods, those relying on knowledge distillation (KD) have received great attention. They leverage knowledge transfer to utilise the labelled data sets created by multiple DA methods instead of directly combining them for training DNNs. However, existing KD-based methods can only utilise certain types of DA methods, incapable of making full use of the advantages of arbitrary DA methods. In this work, we propose a general multi-DA based DNN training framework capable to use arbitrary DA methods. To train a DNN, our framework replicates a certain portion in the latter part of the DNN into multiple copies, leading to multiple DNNs with shared blocks in their former parts and independent blocks in their latter parts. Each of these DNNs is associated with a unique DA and a newly devised loss that allows comprehensively learning from the data generated by all DA methods and the outputs from all DNNs in an online and adaptive way. The overall loss, i.e., the sum of each DNN's loss, is used for training the DNN. Eventually, one of the DNNs with the best validation performance is chosen for inference. We implement the proposed framework by using three distinct DA methods and apply it for training representative DNNs. Experimental results on the popular benchmarks of image classification demonstrate the superiority of our method to several existing single-DA and multi-DA based training methods.

Similar Papers
  • Conference Article
  • Citations32

Optimizing Data Augmentation for Semantic Segmentation on Small-Scale Dataset

  • Jun 15, 2019
  • Rui Ma +2
  • Conference Article
  • Citations227

Environmental Sound Classification Using Deep Convolutional Neural Networks and Data Augmentation

  • Dec 01, 2018
  • Nithya Davis +1
  • PDF
  • Research Article
  • Citations4

Guided Random Mask: Adaptively Regularizing Deep Neural Networks for Medical Image Analysis by Potential Lesions

  • Sep 09, 2022
  • Applied Sciences
  • Xiaorui Yu +2
  • Research Article
  • Citations15

Identifying stable EEG patterns over time for mental workload recognition using transfer DS-CNN framework

  • Nov 15, 2023
  • Biomedical Signal Processing and Control
  • Lin Jin +4
  • PDF
  • Research Article
  • Citations22

Data Augmentation for Building Footprint Segmentation in SAR Images: An Empirical Study

  • Apr 22, 2022
  • Remote Sensing
  • Sandhi Wangiyana +2
  • PDF
  • Research Article
  • Citations22

3D data-augmentation methods for semantic segmentation of tomato plant parts.

  • Jun 12, 2023
  • Frontiers in Plant Science
  • Bolai Xin +3
  • Research Article
  • Citations99

Data augmentation techniques in natural language processing

  • Nov 19, 2022
  • Applied Soft Computing
  • Lucas Francisco Amaral Orosco Pellicer +2
  • Dissertation
  • Citations1

Data Augmentation methods in natural language processing.

  • Jul 20, 2021
  • Taynan Maier Ferreira
  • Research Article
  • Citations70

A review of synthetic and augmented training data for machine learning in ultrasonic non-destructive evaluation

  • May 18, 2023
  • Ultrasonics
  • Sebastian Uhlig +4
  • Research Article
  • Citations59

Mariana

  • Aug 01, 2014
  • Proceedings of the VLDB Endowment
  • Yongqiang Zou +5
  • PDF
  • Conference Article
  • Citations31

Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization

  • Jan 01, 2019
  • Guanlin Li +4
  • Conference Article
  • Citations44

STaDA: Style Transfer as Data Augmentation

  • Jan 01, 2019
  • Xu Zheng +4
  • PDF
  • Research Article
  • Citations1

Graph Empirical Mode Decomposition-Based Data Augmentation Applied to Gifted Children MRI Analysis.

  • Jul 01, 2022
  • Frontiers in Neuroscience
  • Xuning Chen +7
  • PDF
  • Research Article
  • Citations7

AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation

  • Aug 24, 2024
  • International Journal of Computer Vision
  • Lin Li +2
  • Conference Article
  • Citations10

Domain-specific data augmentation for on-road object detection based on a deep neural network

  • Jun 01, 2017
  • Hui Eun Kim +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.