SegNet: A deep convolutional encoder-decoder architecture for image segmentation. We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network. The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN and also with the well known DeepLab-LargeFOV, DeconvNet architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at this http URL

References in zbMATH (referenced in 16 articles )

Showing results 1 to 16 of 16.
Sorted by year (citations)

  1. Alberto Gomez: MIPROT: A Medical Image Processing Toolbox for MATLAB (2021) arXiv
  2. Jia, Fan; Liu, Jun; Tai, Xue-Cheng: A regularized convolutional neural network for semantic image segmentation (2021)
  3. Amosov, O. S.; Amosova, S. G.; Zhiganov, S. V.; Ivanov, Yu. S.; Pashchenko, F. F.: Computational method for recognizing situations and objects in the frames of a continuous video stream using deep neural networks for access control systems (2020)
  4. Badar, Maryam; Haris, Muhammad; Fatima, Anam: Application of deep learning for retinal image analysis: a review (2020)
  5. Hu, Ruimeng: Deep learning for ranking response surfaces with applications to optimal stopping problems (2020)
  6. Jia, Fan; Tai, Xue-Cheng; Liu, Jun: Nonlocal regularized CNN for image segmentation (2020)
  7. Zhang, Hai-Miao; Dong, Bin: A review on deep learning in medical image reconstruction (2020)
  8. Fan, Yuwei; Feliu-Fabà, Jordi; Lin, Lin; Ying, Lexing; Zepeda-Núñez, Leonardo: A multiscale neural network based on hierarchical nested bases (2019)
  9. Fan, Yuwei; Lin, Lin; Ying, Lexing; Zepeda-Núñez, Leonardo: A multiscale neural network based on hierarchical matrices (2019)
  10. Fan, Yuwei; Orozco Bohorquez, Cindy; Ying, Lexing: BCR-net: A neural network based on the nonstandard wavelet form (2019)
  11. Mercadier, Mathieu; Lardy, Jean-Pierre: Credit spread approximation and improvement using random forest regression (2019)
  12. Zhang, Dongkun; Lu, Lu; Guo, Ling; Karniadakis, George Em: Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems (2019)
  13. Mauch, Lukas; Wang, Chunlai; Yang, Bin: Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation (2018)
  14. Saha, Monjoy; Chakraborty, Chandan: Her2Net: a deep framework for semantic segmentation and classification of cell membranes and nuclei in breast cancer evaluation (2018)
  15. Zhu, Yinhao; Zabaras, Nicholas: Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification (2018)
  16. Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele: The Cityscapes Dataset for Semantic Urban Scene Understanding (2016) arXiv