A new multi-scale backbone network for object detection based on asymmetric convolutions

5Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

This article is free to access.

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.

References Powered by Scopus

Deep residual learning for image recognition

174093Citations
N/AReaders
Get full text

You only look once: Unified, real-time object detection

37553Citations
N/AReaders
Get full text

Microsoft COCO: Common objects in context

28812Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Noise Parameter Estimation Two-Stage Network for Single Infrared Dim Small Target Image Destriping

9Citations
N/AReaders
Get full text

Multi-scale adaptive learning network with double connection mechanism for super-resolution on agricultural pest images

2Citations
N/AReaders
Get full text

Irregular feature enhancer for low-dose CT denoising

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Ma, X., & Yang, Z. (2021). A new multi-scale backbone network for object detection based on asymmetric convolutions. Science Progress, 104(2). https://doi.org/10.1177/00368504211011343

Readers' Seniority

Tooltip

Professor / Associate Prof. 1

50%

PhD / Post grad / Masters / Doc 1

50%

Readers' Discipline

Tooltip

Computer Science 2

50%

Biochemistry, Genetics and Molecular Bi... 1

25%

Engineering 1

25%

Save time finding and organizing research with Mendeley

Sign up for free