FastStereoNet: A Fast Neural Architecture Search for Improving the Inference of Disparity Estimation on Resource-Limited Platforms

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: onr:"swepub:oai:DiVA.org:mdh-56844" > FastStereoNet :

1 of 1
Previous record
Next record
To hitlist

FastStereoNet : A Fast Neural Architecture Search for Improving the Inference of Disparity Estimation on Resource-Limited Platforms

Loni, Mohammad, PhD Candidate, 1991- (author): Mälardalens högskola,Inbyggda system

Zoljodi, Ali (author): Mälardalens högskola,Inbyggda system

Majd, Amin (author): Arcada Univ Appl Sci, Dept Econ & Business Anal, Helsinki 00560, Finland.

Ahn, Byung Hoon (author): Univ Calif San Diego, Dept Comp Sci & Engn, Alternat Comp Technol Lab, La Jolla, CA 92093 USA.

Daneshtalab, Masoud (author): Malardalen Univ, Sch Innovat Design & Engn, S-72218 Vasteras, Sweden.;TalTech Univ, Dept Comp Syst, EE-19086 Tallinn, Estonia.

Sjödin, Mikael, 1971- (author): Mälardalens högskola,Inbyggda system,Malardalen Univ, Sch Innovat Design & Engn, S-72218 Vasteras, Sweden.

Esmaeilzadeh, Hadi (author): Univ Calif San Diego, Dept Comp Sci & Engn, Alternat Comp Technol Lab, La Jolla, CA 92093 USA.

show less...

(creator_code:org_t)

Institute of Electrical and Electronics Engineers (IEEE), 2022
2022
English.
In: IEEE Transactions on Systems, Man & Cybernetics. Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 2168-2216 .- 2168-2232. ; 52:8, s. 5222-5234

Related links:: https://urn.kb.se/re...; show more...; https://doi.org/10.1...; show less...

Journal article (peer-reviewed)

Abstract Subject headings

Convolutional neural networks (CNNs) provide the best accuracy for disparity estimation. However, CNNs are computationally expensive, making them unfavorable for resource-limited devices with real-time constraints. Recent advances in neural architectures search (NAS) promise opportunities in automated optimization for disparity estimation. However, the main challenge of the NAS methods is the significant amount of computing time to explore a vast search space [e.g., 1.6x10(29)] and costly training candidates. To reduce the NAS computational demand, many proxy-based NAS methods have been proposed. Despite their success, most of them are designed for comparatively small-scale learning tasks. In this article, we propose a fast NAS method, called FastStereoNet, to enable resource-aware NAS within an intractably large search space. FastStereoNet automatically searches for hardware-friendly CNN architectures based on late acceptance hill climbing (LAHC), followed by simulated annealing (SA). FastStereoNet also employs a fine-tuning with a transferred weights mechanism to improve the convergence of the search process. The collection of these ideas provides competitive results in terms of search time and strikes a balance between accuracy and efficiency. Compared to the state of the art, FastStereoNet provides 5.25x reduction in search time and 44.4x reduction in model size. These benefits are attained while yielding a comparable accuracy that enables seamless deployment of disparity estimation on resource-limited devices. Finally, FastStereoNet significantly improves the perception quality of disparity estimation deployed on field-programmable gate array and Intel Neural Compute Stick 2 accelerator in a significantly less onerous manner.

Subject headings

TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)

Keyword

Disparity estimation
machine vision
neural architecture search
optimization
transfer learning

Publication and Content Type

ref (subject category)
art (subject category)

Find in a library

IEEE Transactions on Systems, Man & Cybernetics. Systems (Search for host publication in LIBRIS)

To the university's database

1 of 1
Previous record
Next record
To hitlist

Find more in SwePub

By the author/editor: Loni, Mohammad, ...; Zoljodi, Ali; Majd, Amin; Ahn, Byung Hoon; Daneshtalab, Mas ...; Sjödin, Mikael, ...; show more...; Esmaeilzadeh, Ha ...; show less...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Computer Systems

Articles in the publication: IEEE Transaction ...

By the university: Mälardalen University

Search outside SwePub

Extend your search to:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se