Skip to Main content Skip to Navigation
Journal articles

Deep Model Compression and Architecture Optimization for Embedded Systems: A Survey

Abstract : Over the past, deep neural networks have proved to be an essential element for developing intelligent solutions. They have achieved remarkable performances at a cost of deeper layers and millions of parameters. Therefore utilising these networks on limited resource platforms for smart cameras is a challenging task. In this context, models need to be (i) accelerated and (ii) memory efficient without significantly compromising on performance. Numerous works have been done to obtain smaller, faster and accurate models. This paper presents a survey of methods suitable for porting deep neural networks on resource-limited devices, especially for smart cameras. These methods can be roughly divided in two main sections. In the first part, we present compression techniques. These techniques are categorized into: knowledge distillation, pruning, quantization, hashing, reduction of numerical precision and binarization. In the second part, we focus on architecture optimization. We introduce the methods to enhance networks structures as well as neural architecture search techniques. In each of their parts, we describe different methods, and analyse them. Finally, we conclude this paper with a discussion on these methods.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03048735
Contributor : Anthony Berthelier Connect in order to contact the contributor
Submitted on : Wednesday, December 9, 2020 - 3:03:37 PM
Last modification on : Thursday, September 9, 2021 - 2:36:02 PM
Long-term archiving on: : Wednesday, March 10, 2021 - 7:24:25 PM

File

Compression_Survey_hal.pdf
Files produced by the author(s)

Identifiers

Citation

Anthony Berthelier, Thierry Chateau, Stefan Duffner, Christophe Garcia, Christophe Blanc. Deep Model Compression and Architecture Optimization for Embedded Systems: A Survey. Journal of Signal Processing Systems, Springer, 2020, ⟨10.1007/s11265-020-01596-1⟩. ⟨hal-03048735⟩

Share

Metrics

Record views

125

Files downloads

763