RMF-Net: Improving Object Detection with Multi-scale Strategy

2021 ◽  
Author(s):  
Yanyan ZHANG ◽  
Meiling SHEN ◽  
Wensheng YANG
Keyword(s):  
Object Detection ◽  
Multi Scale

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

2021 ◽  
Vol 104 (2) ◽  
pp. 003685042110113
Author(s):  
Xianghua Ma ◽  
Zhenkun Yang
Keyword(s):  
Object Detection ◽  
Image Features ◽  
Detection Accuracy ◽  
Mobile Platforms ◽  
Multi Scale ◽  
Backbone Network ◽  
Aspect Ratios ◽  
Pascal Voc ◽  
Scale Characteristics ◽  
Detection Speed

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.

Multi-scale object detection for high-speed railway clearance intrusion

2021 ◽  
Author(s):  
Runliang Tian ◽  
Hongmei Shi ◽  
Baoqing Guo ◽  
Liqiang Zhu
Keyword(s):  
Object Detection ◽  
High Speed ◽  
High Speed Railway ◽  
Multi Scale

An Efficient Implementation of FPGA-based Object Detection Using Multi-scale Attention

2021 ◽  
Author(s):  
Masanori Furuta ◽  
Koichiro Ban ◽  
Daisuke Kobayashi ◽  
Tomoyuki Shibata
Keyword(s):  
Object Detection ◽  
Efficient Implementation ◽  
Multi Scale

An Improved Bounding Box Regression Loss Function Based on CIOU Loss for Multi-scale Object Detection

2021 ◽  
Author(s):  
Shuangjiang Du ◽  
Baofu Zhang ◽  
Pin Zhang ◽  
Peng Xiang
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Multi Scale ◽  
Bounding Box

Multi-scale Object Detection Algorithm in Smart City Based on Mixed Dilated Convolution Pyramid

2021 ◽  
Author(s):  
Kangning Yin ◽  
Jie Liang ◽  
Shaoqi Hou ◽  
Rui Zhu ◽  
Guangqiang Yin ◽  
...  
Keyword(s):  
Object Detection ◽  
Smart City ◽  
Detection Algorithm ◽  
Multi Scale ◽  
Dilated Convolution

Flexible feature-space-construction architecture and its VLSI implementation for multi-scale object detection

2018 ◽  
Vol 57 (4S) ◽  
pp. 04FF04
Author(s):  
Aiwen Luo ◽  
Fengwei An ◽  
Xiangyu Zhang ◽  
Lei Chen ◽  
Zunkai Huang ◽  
...  
Keyword(s):  
Object Detection ◽  
Feature Space ◽  
Vlsi Implementation ◽  
Multi Scale ◽  
Space Construction

scholarly journals Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images

2020 ◽  
Vol 12 (5) ◽  
pp. 784 ◽  
Author(s):  
Wei Guo ◽  
Weihong Li ◽  
Weiguo Gong ◽  
Jinkai Cui
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Semantic Information ◽  
Aerial Images ◽  
Training Strategy ◽  
The Public ◽  
Multi Scale ◽  
Shallow Layer ◽  
The Neural Network ◽  
Feature Pyramid

Multi-scale object detection is a basic challenge in computer vision. Although many advanced methods based on convolutional neural networks have succeeded in natural images, the progress in aerial images has been relatively slow mainly due to the considerably huge scale variations of objects and many densely distributed small objects. In this paper, considering that the semantic information of the small objects may be weakened or even disappear in the deeper layers of neural network, we propose a new detection framework called Extended Feature Pyramid Network (EFPN) for strengthening the information extraction ability of the neural network. In the EFPN, we first design the multi-branched dilated bottleneck (MBDB) module in the lateral connections to capture much more semantic information. Then, we further devise an attention pathway for better locating the objects. Finally, an augmented bottom-up pathway is conducted for making shallow layer information easier to spread and further improving performance. Moreover, we present an adaptive scale training strategy to enable the network to better recognize multi-scale objects. Meanwhile, we present a novel clustering method to achieve adaptive anchors and make the neural network better learn data features. Experiments on the public aerial datasets indicate that the presented method obtain state-of-the-art performance.

Sign in / Sign up

Export Citation Format

Share Document