GhostShiftAddNet: More Features from Energy-Efficient Operations Article Swipe

MAKE IMPACT

Jia Bi , Jonathon Hare , Geoff V. Merrett · YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2109.09495

Deep convolutional neural networks (CNNs) are computationally and memory intensive. In CNNs, intensive multiplication can have resource implications that may challenge the ability for effective deployment of inference on resource-constrained edge devices. This paper proposes GhostShiftAddNet, where the motivation is to implement a hardware-efficient deep network: a multiplication-free CNN with fewer redundant features. We introduce a new bottleneck block, GhostSA, that converts all multiplications in the block to cheap operations. The bottleneck uses an appropriate number of bit-shift filters to process intrinsic feature maps, then applies a series of transformations that consist of bit-wise shifts with addition operations to generate more feature maps that fully learn to capture information underlying intrinsic features. We schedule the number of bit-shift and addition operations for different hardware platforms. We conduct extensive experiments and ablation studies with desktop and embedded (Jetson Nano) devices for implementation and measurements. We demonstrate the proposed GhostSA block can replace bottleneck blocks in the backbone of state-of-the-art networks architectures and gives improved performance on image classification benchmarks. Further, our GhostShiftAddNet can achieve higher classification accuracy with fewer FLOPs and parameters (reduced by up to 3x) than GhostNet. When compared to GhostNet, inference latency on the Jetson Nano is improved by 1.3x and 2x on the GPU and CPU respectively. Code is available open-source on \url{https://github.com/JIABI/GhostShiftAddNet}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2109.09495

PDF

https://arxiv.org/pdf/2109.09495

OA Status

green

Related Works

10

OpenAlex ID

https://openalex.org/W4286970480

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4286970480

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2109.09495

Digital Object Identifier

Title

GhostShiftAddNet: More Features from Energy-Efficient Operations

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-09-20

Full publication date if available

Authors

Jia Bi, Jonathon Hare, Geoff V. Merrett

List of authors in order

Landing page

https://arxiv.org/abs/2109.09495

Publisher landing page

PDF URL

https://arxiv.org/pdf/2109.09495

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2109.09495

Direct OA link when available

Concepts

Bottleneck, Computer science, Convolutional neural network, Block (permutation group theory), Inference, Latency (audio), Feature (linguistics), Deep learning, Computer engineering, Parallel computing, Artificial intelligence, Embedded system, Linguistics, Geometry, Philosophy, Telecommunications, Mathematics

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload