Skip to Main content Skip to Navigation
Conference papers

Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems

Abstract : Employing convolutional neural network models for large scale datasets represents a big challenge. Especially embedded devices with limited resources cannot run most state-of-the-art model architectures in real-time, necessary for many applications. This paper proves the applicability of shunt connections on large scale datasets and narrows this computational gap. Shunt connections is a proposed method for MobileNet compression. We are the first to provide results of shunt connections for the MobileNetV3 model and for segmentation tasks on the Cityscapes dataset, using the DeeplabV3 architecture, on which we achieve compression by 28%, while observing a 3.52 drop in mIoU. The training of shunt-inserted models are optimized through knowledge distillation. The full code used for this work will be available online.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03287657
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, July 15, 2021 - 6:09:38 PM
Last modification on : Wednesday, October 13, 2021 - 7:58:04 PM
Long-term archiving on: : Saturday, October 16, 2021 - 7:02:23 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2024-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Bernhard Haas, Alexander Wendt, Axel Jantsch, Matthias Wess. Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.349-361, ⟨10.1007/978-3-030-79150-6_28⟩. ⟨hal-03287657⟩

Share

Metrics

Record views

21