« Previous AbstractComprehensive evaluation of ionic liquid [Bmim][PF(6)] for absorbing toluene and acetone    Next AbstractAdsorption/desorption characteristics of low-concentration semi-volatile organic compounds in vapor phase on activated carbon »

Sci Prog

Title:		A new multi-scale backbone network for object detection based on asymmetric convolutions
Author(s):		Ma X; Yang Z;
Address:		"School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, China"
Journal Title:		Sci Prog
Year:		2021
Volume:		104
Issue:		2
Page Number:		3.68504E+14 -
DOI:		10.1177/00368504211011343
ISSN/ISBN:		2047-7163 (Electronic) 0036-8504 (Print) 0036-8504 (Linking)
Abstract:		"Real-time object detection on mobile platforms is a crucial but challenging computer vision task. However, it is widely recognized that although the lightweight object detectors have a high detection speed, the detection accuracy is relatively low. In order to improve detecting accuracy, it is beneficial to extract complete multi-scale image features in visual cognitive tasks. Asymmetric convolutions have a useful quality, that is, they have different aspect ratios, which can be used to exact image features of objects, especially objects with multi-scale characteristics. In this paper, we exploit three different asymmetric convolutions in parallel and propose a new multi-scale asymmetric convolution unit, namely MAC block to enhance multi-scale representation ability of CNNs. In addition, MAC block can adaptively merge the features with different scales by allocating learnable weighted parameters to three different asymmetric convolution branches. The proposed MAC blocks can be inserted into the state-of-the-art backbone such as ResNet-50 to form a new multi-scale backbone network of object detectors. To evaluate the performance of MAC block, we conduct experiments on CIFAR-100, PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO 2014 datasets. Experimental results show that the detection precision can be greatly improved while a fast detection speed is guaranteed as well"
Keywords:		"*Neural Networks, Computer Records *Volatile Organic Compounds Object detection asymmetric convolutions backbone network deep learning multi-scale representation;"
Notes:		"MedlineMa, Xianghua Yang, Zhenkun eng Research Support, Non-U.S. Gov't England 2021/04/22 Sci Prog. 2021 Apr-Jun; 104(2):368504211011343. doi: 10.1177/00368504211011343"