DBGC: Dimension-Based Generic Convolution Block for Object Recognition

Sensors

Hemant Ghayvat¹  Muhammad Ahmed Khan²  Urvashi Sharma³  Chirag Patel³  Khushi Patel³  Mohd Zuhair⁴  Shubhankar Majumdar⁵  Nagaraj Cholli⁶  Akash Patel⁷  Urvi Bhatt⁷  Radhika Patel⁷  Syed Aziz Shah⁸  Dulari Bhatt⁹  Kirit Modi^1,10  Sharnil Pandya^1,11 

[1] Computer Science Department, Faculty of Technology, Linnaeus University, P G Vejdes väg, 351 95 Växjö, Sweden;DTU Health Tech Department of Health Technology, 247 99 Lyngby, Denmark;Department of Computer Engineering, Devang Patel Institute of Advance Technology and Research (DEPSTAR), Faculty of Technology and Engineering (FTE), CHARUSAT Campus, Charotar University of Science and Technology (CHARUSAT), Changa 388421, India;Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, India;Department of Electronics and Communication Engineering, National Institute of Technology, Bijni Complex, Laitumkhrah, Shillong 793003, Meghalaya, India;Department of Information Science and Engineering, R. V. College of Engineering, Banglore 560059, India;Department of Information Technology, Devang Patel Institute of Advance Technology and Research (DEPSTAR), Faculty of Technology and Engineering (FTE), CHARUSAT Campus, Charotar University of Science and Technology (CHARUSAT), Changa 388421, India;Healthcare Technology and Innovation Theme, Faculty Research Centre for Intelligent Healthcare, Coventry University, Richard Crossman Building, Coventry CV1 5RW, UK;Parul University, Vadodara 382030, Gujarat, India;Sankalchand Patel College of Engineering, Sankalchand Patel University, Visnagar 384315, India;Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune 412115, India;

关键词: CNN;    separable convolution;    DBGC;    dimension-based kernels;   

DOI  :  10.3390/s22051780

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown