Sökning: onr:"swepub:oai:DiVA.org:lnu-111487" >
DBGC :
DBGC : Dimension-Based Generic Convolution Block for Object Recognition
-
- Patel, Chirag (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
- Bhatt, Dulari (författare)
- Parul Univ, India
-
- Sharma, Urvashi (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
visa fler...
-
- Patel, Radhika (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
- Pandya, Sharnil (författare)
- Symbiosis Int Deemed Univ, India
-
- Modi, Kirit (författare)
- Sankalchand Patel Univ, India
-
- Cholli, Nagaraj (författare)
- RV Coll Engn, India
-
- Patel, Akash (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
- Bhatt, Urvi (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
- Khan, Muhammad Ahmed (författare)
- DTU Hlth Tech Dept Hlth Technol, Denmark
-
- Majumdar, Shubhankar (författare)
- Natl Inst Technol, India
-
- Zuhair, Mohd (författare)
- Nirma Univ, India
-
- Patel, Khushi (författare)
- Charotar Univ Sci & Technol CHARUSAT, India
-
- Shah, Syed Aziz (författare)
- Coventry Univ, UK
-
- Ghayvat, Hemant (författare)
- Linnéuniversitetet,Institutionen för datavetenskap och medieteknik (DM),DISA;DISA-IDP;DISA-SIG ; AiHealth
-
visa färre...
-
(creator_code:org_t)
- 2022-02-24
- 2022
- Engelska.
-
Ingår i: Sensors. - : MDPI. - 1424-8220. ; 22:5
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://lnu.diva-por... (primary) (Raw object)
-
https://www.mdpi.com...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic object or activity detection from images or video. Increases in the use of various sensor networks have also raised the need of lightweight process frameworks. Much research has been carried out in this area, but the research scope is colossal as it deals with open-ended problems such as being able to achieve high accuracy in little time using lightweight process frameworks. Convolution Neural Networks and their variants are widely used in various computer vision activities, but most of the architectures of CNN are application-specific. There is always a need for generic architectures with better performance. This paper introduces the Dimension-Based Generic Convolution Block (DBGC), which can be used with any CNN to make the architecture generic and provide a dimension-wise selection of various height, width, and depth kernels. This single unit which uses the separable convolution concept provides multiple combinations using various dimension-based kernels. This single unit can be used for height-based, width-based, or depth-based dimensions; the same unit can even be used for height and width, width and depth, and depth and height dimensions. It can also be used for combinations involving all three dimensions of height, width, and depth. The main novelty of DBGC lies in the dimension selector block included in the proposed architecture. Proposed unoptimized kernel dimensions reduce FLOPs by around one third and also reduce the accuracy by around one half; semi-optimized kernel dimensions yield almost the same or higher accuracy with half the FLOPs of the original architecture, while optimized kernel dimensions provide 5 to 6% higher accuracy with around a 10 M reduction in FLOPs.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- CNN
- separable convolution
- DBGC
- dimension-based kernels
- Computer Science
- Datavetenskap
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
-
Sensors
(Sök värdpublikationen i LIBRIS)
Till lärosätets databas
- Av författaren/redakt...
-
Patel, Chirag
-
Bhatt, Dulari
-
Sharma, Urvashi
-
Patel, Radhika
-
Pandya, Sharnil
-
Modi, Kirit
-
visa fler...
-
Cholli, Nagaraj
-
Patel, Akash
-
Bhatt, Urvi
-
Khan, Muhammad A ...
-
Majumdar, Shubha ...
-
Zuhair, Mohd
-
Patel, Khushi
-
Shah, Syed Aziz
-
Ghayvat, Hemant
-
visa färre...
- Om ämnet
-
- NATURVETENSKAP
-
NATURVETENSKAP
-
och Data och informa ...
-
och Datavetenskap
- Artiklar i publikationen
-
Sensors
- Av lärosätet
-
Linnéuniversitetet