DBGC: Dimension-Based Generic Convolution Block for Object Recognition
Chirag Patel,
Dulari Bhatt,
Urvashi Sharma,
Radhika Patel,
Sharnil Pandya,
Kirit Modi,
Nagaraj Cholli,
Akash Patel,
Urvi Bhatt,
Muhammad Ahmed Khan,
Shubhankar Majumdar,
Mohd Zuhair,
Khushi Patel,
Syed Aziz Shah,
Hemant Ghayvat
Affiliations
Chirag Patel
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
Dulari Bhatt
Parul University, Vadodara 382030, Gujarat, India
Urvashi Sharma
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
Radhika Patel
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
Sharnil Pandya
Symbiosis Institute of Technology, Symbiosis International (Deemed) University, Pune 412115, India
Kirit Modi
Sankalchand Patel College of Engineering, Sankalchand Patel University, Visnagar 384315, India
Nagaraj Cholli
Department of Information Science and Engineering, R. V. College of Engineering, Banglore 560059, India
Akash Patel
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
Urvi Bhatt
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
Muhammad Ahmed Khan
DTU Health Tech Department of Health Technology, 247 99 Lyngby, Denmark
Shubhankar Majumdar
Department of Electronics and Communication Engineering, National Institute of Technology, Bijni Complex, Laitumkhrah, Shillong 793003, Meghalaya, India
Mohd Zuhair
Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, India
Khushi Patel
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
Syed Aziz Shah
Healthcare Technology and Innovation Theme, Faculty Research Centre for Intelligent Healthcare, Coventry University, Richard Crossman Building, Coventry CV1 5RW, UK
Hemant Ghayvat
Computer Science Department, Faculty of Technology, Linnaeus University, P G Vejdes väg, 351 95 Växjö, Sweden
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.
