Search: id:"swepub:oai:DiVA.org:miun-43421" >
Neural Network Comp...
Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems
- Article/chapterEnglish2021
Publisher, publication year, extent ...
-
2021-06-22
-
Cham :Springer Science and Business Media Deutschland GmbH,2021
-
printrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:miun-43421
-
https://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-43421URI
-
https://doi.org/10.1007/978-3-030-79150-6_28DOI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:kon swepub-publicationtype
Notes
-
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. © 2021, IFIP International Federation for Information Processing.
Subject headings and genre
-
Accuracy
-
CIFAR
-
Cityscapes
-
DeepLab
-
Embedded machine learning
-
Knowledge distillation
-
Latency
-
Machine learning
-
MobileNet
-
Optimization
-
Shunt connections
-
Convolutional neural networks
-
Distillation
-
Large dataset
-
Network architecture
-
Semantic Web
-
Semantics
-
Embedded device
-
Large-scale datasets
-
Network compression
-
Real time
-
Semantic segmentation
-
State of the art
-
Distilleries
Added entries (persons, corporate bodies, meetings, titles ...)
-
Wendt, A.
(author)
-
Jantsch, A.
(author)
-
Wess, M.
(author)
Related titles
-
In:IFIP Advances in Information and Communication TechnologyCham : Springer Science and Business Media Deutschland GmbH, s. 349-3619783030791490
Internet link
Find in a library
To the university's database