Lightweight Monocular Depth with a Novel Neural Architecture Search Method
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00362944" target="_blank" >RIV/68407700:21230/22:00362944 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/WACV51458.2022.00040" target="_blank" >https://doi.org/10.1109/WACV51458.2022.00040</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/WACV51458.2022.00040" target="_blank" >10.1109/WACV51458.2022.00040</a>
Alternative languages
Result language
angličtina
Original language name
Lightweight Monocular Depth with a Novel Neural Architecture Search Method
Original language description
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture search (NAS) approaches, where finding optimized networks is computationally demanding, the introduced novel Assisted Tabu Search leads to efficient architecture exploration. Moreover, we construct the search space on a pre-defined backbone network to balance layer diversity and search space size. The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance. The LiDNAS optimized models achieve result superior to compact depth estimation state-of-the-art on NYU-Depth-v2, KITTI, and ScanNet, while being 7%-500% more compact in size, i.e the number of model parameters.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
ISBN
978-1-6654-0915-5
ISSN
2472-6737
e-ISSN
2642-9381
Number of pages
11
Pages from-to
326-336
Publisher name
IEEE Computer Society
Place of publication
USA
Event location
Waikoloa
Event date
Jan 3, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000800471200033