Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

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

Résumé

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.
Fichier principal
Vignette du fichier
509922_1_En_28_Chapter.pdf (309.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03287657 , version 1 (15-07-2021)

Licence

Paternité

Identifiants

Citer

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⟩
34 Consultations
34 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More