TY - JOUR
T1 - DBGC
T2 - Dimension-Based Generic Convolution Block for Object Recognition
AU - Patel, Chirag
AU - Bhatt, Dulari
AU - Sharma, Urvashi
AU - Patel, Radhika
AU - Pandya, Sharnil
AU - Modi, Kirit
AU - Cholli, Nagaraj
AU - Patel, Akash
AU - Bhatt, Urvi
AU - Khan, Muhammad Ahmed
AU - Majumdar, Shubhankar
AU - Zuhair, Mohd
AU - Patel, Khushi
AU - Shah, Syed Aziz
AU - Ghayvat, Hemant
PY - 2022/2/24
Y1 - 2022/2/24
N2 - 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.
AB - 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.
KW - CNN
KW - DBGC
KW - Dimension-based kernels
KW - Separable convolution
UR - http://www.scopus.com/inward/record.url?scp=85125090746&partnerID=8YFLogxK
U2 - 10.3390/s22051780
DO - 10.3390/s22051780
M3 - Article
C2 - 35270929
AN - SCOPUS:85125090746
SN - 1424-8220
VL - 22
JO - Sensors
JF - Sensors
IS - 5
M1 - 1780
ER -