Detail publikace

Upsampling Algorithms for Autoencoder Segmentation Neural Networks: A Comparison Study

Originální název

Upsampling Algorithms for Autoencoder Segmentation Neural Networks: A Comparison Study

Anglický název

Upsampling Algorithms for Autoencoder Segmentation Neural Networks: A Comparison Study

Jazyk

en

Originální abstrakt

This paper compares nine different upsampling methods used in convolutional neural networks in terms of accuracy and processing speed. The process of image segmentation using autoencoder neural networks consists of the image downsampling in the encoder and correspondingly of image upsampling in the decoder part of the network to achieve original image resolution. This paper focuses on the upsampling process in the decoder part of the standard U-Net neural network. Three different interpolations are compared with and without subsequent 1x1 convolution layers and three transpose convolution layers for image upsampling using different size convolutional cores. The experiment has shown that the best practical results were achieved using simple nearest neighbor interpolation upsampling taking into consideration the computational time needed. The network using nearest neighbor interpolation upsampling achieved pixel accuracy of 99.47\% and has shown fast training time and convergence in comparison with other networks using different upsampling methods. The data used in this work consist of a lumbar CT spine segmentation dataset.

Anglický abstrakt

This paper compares nine different upsampling methods used in convolutional neural networks in terms of accuracy and processing speed. The process of image segmentation using autoencoder neural networks consists of the image downsampling in the encoder and correspondingly of image upsampling in the decoder part of the network to achieve original image resolution. This paper focuses on the upsampling process in the decoder part of the standard U-Net neural network. Three different interpolations are compared with and without subsequent 1x1 convolution layers and three transpose convolution layers for image upsampling using different size convolutional cores. The experiment has shown that the best practical results were achieved using simple nearest neighbor interpolation upsampling taking into consideration the computational time needed. The network using nearest neighbor interpolation upsampling achieved pixel accuracy of 99.47\% and has shown fast training time and convergence in comparison with other networks using different upsampling methods. The data used in this work consist of a lumbar CT spine segmentation dataset.

BibTex


@inproceedings{BUT159728,
  author="Martin {Kolařík} and Radim {Burget} and Kamil {Říha}",
  title="Upsampling Algorithms for Autoencoder Segmentation Neural Networks: A Comparison Study",
  annote="This paper compares nine different upsampling methods used in convolutional neural networks in terms of accuracy and processing speed. The process of image segmentation using autoencoder neural networks consists of the image downsampling in the encoder and correspondingly of image upsampling in the decoder part of the network to achieve original image resolution. This paper focuses on the upsampling process in the decoder part of the standard U-Net neural network. Three different interpolations are compared with and without subsequent 1x1 convolution layers and three transpose convolution layers for image upsampling using different size convolutional cores. The experiment has shown that the best practical results were achieved using simple nearest neighbor interpolation upsampling taking into consideration the computational time needed. The network using nearest neighbor interpolation upsampling achieved pixel accuracy of 99.47\% and has shown fast training time and convergence in comparison with other networks using different upsampling methods. The data used in this work consist of a lumbar CT spine segmentation dataset.",
  booktitle="2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  chapter="159728",
  doi="10.1109/ICUMT48472.2019.8970918",
  howpublished="online",
  year="2019",
  month="october",
  pages="1--5",
  type="conference paper"
}