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.
Highlights
The Convolution Neural Network is a widely used deep learning architecture for computer vision tasks such as object detection, object segmentation, and object recognition [1]
ShuffleNetv2 architecture, evaluated the generic nature of the unit on the dataset explained in we evaluated the generic nature of the Dimension-Based Generic Convolution Block (DBGC) unit on the PASCAL VOC dataset explained Section
DBGC was used with ESPNetv2 and ShuffleNetv2 architectures
Summary
The Convolution Neural Network is a widely used deep learning architecture for computer vision tasks such as object detection, object segmentation, and object recognition [1]. This module can be added into any architecture to reduce numbers of FLOPs without affecting accuracy. Two main contributions of the research lie in developing semi-optimized kernel and optimized kernel methods. Such methods reduce the number of FLOPs while providing equal or greater accuracy. An important task for any computer vision application is to extract correct features [20] It is mentioned in paper [21] that fusion methods for extracting features can be used for better performance. The following sections explain the basic architectures of each of these networks, and states their merits and demerits
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
