Squeeze-SegNet: A new fast deep convolutional neural network for semantic segmentation

Geraldin Nanfack, Azeddine Elhassouny, Rachid Oulad Haj Thami

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution


The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet.

Original languageEnglish
Title of host publicationTenth International Conference on Machine Vision, ICMV 2018
EditorsJianhong Zhou, Antanas Verikas, Dmitry Nikolaev, Petia Radeva
ISBN (Electronic)9781510619418
Publication statusPublished - 2018
Externally publishedYes
Event10th International Conference on Machine Vision, ICMV 2017 - Vienna, Austria
Duration: 13 Nov 201715 Nov 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


Conference10th International Conference on Machine Vision, ICMV 2017


  • autonomous driving
  • city scenes
  • Deep learning
  • encoder-decoder
  • SegNet
  • semantic segmentation
  • SqueezeNet


Dive into the research topics of 'Squeeze-SegNet: A new fast deep convolutional neural network for semantic segmentation'. Together they form a unique fingerprint.

Cite this