17th AIAI 2021, 25 - 27 June 2021, Greece

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

Bernhard Haas, Alexander Wendt, Axel Jantsch, Matthias Wess

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.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.