Next Article in Journal
THBase: A Coprocessor-Based Scheme for Big Trajectory Data Management
Next Article in Special Issue
Forward-Looking Element Recognition Based on the LSTM-CRF Model with the Integrity Algorithm
Previous Article in Journal
An Agent Based Model to Analyze the Bitcoin Mining Activity and a Comparison with the Gold Mining Industry
Previous Article in Special Issue
Bidirectional Recurrent Neural Network Approach for Arabic Named Entity Recognition
Article

Object Detection Network Based on Feature Fusion and Attention Mechanism

1
School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
2
Shanghai Institute for Advanced Communication and Data Science, Shanghai 200444, China
3
The 32nd Research Institute, China Electronics Technology Group Corporation, No. 63 Chengliugong Road, Jiading District, Shanghai 200444, China
*
Author to whom correspondence should be addressed.
Future Internet 2019, 11(1), 9; https://doi.org/10.3390/fi11010009
Received: 9 November 2018 / Revised: 20 December 2018 / Accepted: 25 December 2018 / Published: 2 January 2019
(This article belongs to the Special Issue Innovative Topologies and Algorithms for Neural Networks)
In recent years, almost all of the current top-performing object detection networks use CNN (convolutional neural networks) features. State-of-the-art object detection networks depend on CNN features. In this work, we add feature fusion in the object detection network to obtain a better CNN feature, which incorporates well deep, but semantic, and shallow, but high-resolution, CNN features, thus improving the performance of a small object. Also, the attention mechanism was applied to our object detection network, AF R-CNN (attention mechanism and convolution feature fusion based object detection), to enhance the impact of significant features and weaken background interference. Our AF R-CNN is a single end to end network. We choose the pre-trained network, VGG-16, to extract CNN features. Our detection network is trained on the dataset, PASCAL VOC 2007 and 2012. Empirical evaluation of the PASCAL VOC 2007 dataset demonstrates the effectiveness and improvement of our approach. Our AF R-CNN achieves an object detection accuracy of 75.9% on PASCAL VOC 2007, six points higher than Faster R-CNN. View Full-Text
Keywords: CNN; object detection network; attention mechanism; feature fusion CNN; object detection network; attention mechanism; feature fusion
Show Figures

Figure 1

MDPI and ACS Style

Zhang, Y.; Chen, Y.; Huang, C.; Gao, M. Object Detection Network Based on Feature Fusion and Attention Mechanism. Future Internet 2019, 11, 9. https://doi.org/10.3390/fi11010009

AMA Style

Zhang Y, Chen Y, Huang C, Gao M. Object Detection Network Based on Feature Fusion and Attention Mechanism. Future Internet. 2019; 11(1):9. https://doi.org/10.3390/fi11010009

Chicago/Turabian Style

Zhang, Ying, Yimin Chen, Chen Huang, and Mingke Gao. 2019. "Object Detection Network Based on Feature Fusion and Attention Mechanism" Future Internet 11, no. 1: 9. https://doi.org/10.3390/fi11010009

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop