DBGC: Dimension-Based Generic Convolution Block for Object Recognition
Authors:
- Chirag PatelCPChirag Patel
- Dulari BhattDulari Bhatt
- Urvashi SharmaUSUrvashi Sharma
- Radhika PatelRPRadhika Patel
- Sharnil PandyaSharnil Pandya
- Kirit ModiKMKirit Modi
- Nagaraj CholliNCNagaraj Cholli
- Akash PatelAPAkash Patel
- Urvi BhattUBUrvi Bhatt
- Muhammad Ahmed KhanMKMuhammad Ahmed Khan
- Shubhankar MajumdarShubhankar Majumdar
- Mohd ZuhairMZMohd Zuhair
Open Access
Abstract
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.Keywords
This publication has 16 references indexed in Scilit:
- CP-BDHCA: Blockchain-Based Confidentiality-Privacy Preserving Big Data Scheme for Healthcare Clouds and ApplicationsIEEE Journal of Biomedical and Health Informatics, 2021
- Histogram of Oriented Gradient-Based Fusion of Features for Human Action Recognition in Action Video SequencesSensors, 2020
- DiCENet: Dimension-Wise Convolutions for Efficient NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- IoT Based Emergency Health Monitoring System2020
- Depthwise separable convolution architectures for plant disease classificationComputers and Electronics in Agriculture, 2019
- Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based SteganalysisIEEE Transactions on Information Forensics and Security, 2019
- A 3D Convolutional Neural Network for Volumetric Image Semantic SegmentationProcedia Manufacturing, 2019
- Human action recognition using fusion of features for unconstrained video sequencesComputers and Electrical Engineering, 2018
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Robust Face Recognition Using Distance MatriceInternational Journal of Computer and Electrical Engineering, 2013