Detail publikace

A Perspective of the Noise Removal for Faster Neural Network Training

Originální název

A Perspective of the Noise Removal for Faster Neural Network Training

Anglický název

A Perspective of the Noise Removal for Faster Neural Network Training

Jazyk

en

Originální abstrakt

Image classification is widely used within image processing area. It is known that insufficient amount of data has negative impact on the training of neural networks in terms of accuracy, convergence speed and in some cases even in the inability to converge. On the other hand, big amount of data significantly increases the training time and costs needed for model creation. Every training sample contains the part valuable for decision (face in case of this paper) and noise, i.e. background of the object. This paper introduces method of iterative noise removal during the training with combination with the transfer learning to optimize the speed of the training process. We show the combination of proposed noise removal and transfer learning leads to more effective training process and enables to learn also from limited data sets. The main contribution of this paper is a proposed method that reduces training time and it is able to accelerate the process in average by 69%. The method was tested on binary classification of two persons from LFW database.

Anglický abstrakt

Image classification is widely used within image processing area. It is known that insufficient amount of data has negative impact on the training of neural networks in terms of accuracy, convergence speed and in some cases even in the inability to converge. On the other hand, big amount of data significantly increases the training time and costs needed for model creation. Every training sample contains the part valuable for decision (face in case of this paper) and noise, i.e. background of the object. This paper introduces method of iterative noise removal during the training with combination with the transfer learning to optimize the speed of the training process. We show the combination of proposed noise removal and transfer learning leads to more effective training process and enables to learn also from limited data sets. The main contribution of this paper is a proposed method that reduces training time and it is able to accelerate the process in average by 69%. The method was tested on binary classification of two persons from LFW database.

BibTex


@inproceedings{BUT159767,
  author="Martin {Rajnoha} and Vojtěch {Mikulec} and Radim {Burget} and Jiří {Dražil}",
  title="A Perspective of the Noise Removal for Faster Neural Network Training",
  annote="Image classification is widely used within image processing area. It is known that insufficient amount of data
has negative impact on the training of neural networks in terms of accuracy, convergence speed and in some cases even in the inability to converge. On the other hand, big amount of data significantly increases the training time and costs needed for model creation. Every training sample contains the part valuable for decision (face in case of this paper) and noise, i.e. background of the object. This paper introduces method of iterative noise removal during the training with combination with the transfer learning to optimize the speed of the training process. We show the combination of proposed noise removal and transfer learning leads to more effective training process and enables to learn also from limited data sets. The main contribution of this paper is
a proposed method that reduces training time and it is able to accelerate the process in average by 69%. The method was tested on binary classification of two persons from LFW database.",
  booktitle="2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  chapter="159767",
  doi="10.1109/ICUMT48472.2019.8970907",
  howpublished="online",
  year="2019",
  month="october",
  pages="1--4",
  type="conference paper"
}