Open Access
ARTICLE
An Improved Deep Fusion CNN for Image Recognition
Rongyu Chen1, Lili Pan1, *, Cong Li1, Yan Zhou1, Aibin Chen1, Eric Beckman2
1 College of Computer Science and Information Technology, Central South University of Forestry & Technology, Changsha, 410114, China.
2 China Chaplin School of Hospitality of Hospitality and Tourism Management, Florida International University, North Miami, 33181, USA.
* Corresponding Author: Lili Pan. Email: lily_pan163.com.
Computers, Materials & Continua 2020, 65(2), 1691-1706. https://doi.org/10.32604/cmc.2020.011706
Received 25 May 2020; Accepted 23 June 2020; Issue published 20 August 2020
Abstract
With the development of Deep Convolutional Neural Networks (DCNNs), the
extracted features for image recognition tasks have shifted from low-level features to the
high-level semantic features of DCNNs. Previous studies have shown that the deeper the
network is, the more abstract the features are. However, the recognition ability of deep
features would be limited by insufficient training samples. To address this problem, this
paper derives an improved Deep Fusion Convolutional Neural Network (DF-Net) which
can make full use of the differences and complementarities during network learning and
enhance feature expression under the condition of limited datasets. Specifically, DF-Net
organizes two identical subnets to extract features from the input image in parallel, and
then a well-designed fusion module is introduced to the deep layer of DF-Net to fuse the
subnet’s features in multi-scale. Thus, the more complex mappings are created and the
more abundant and accurate fusion features can be extracted to improve recognition
accuracy. Furthermore, a corresponding training strategy is also proposed to speed up the
convergence and reduce the computation overhead of network training. Finally, DF-Nets
based on the well-known ResNet, DenseNet and MobileNetV2 are evaluated on
CIFAR100, Stanford Dogs, and UECFOOD-100. Theoretical analysis and experimental
results strongly demonstrate that DF-Net enhances the performance of DCNNs and
increases the accuracy of image recognition.
Keywords
Cite This Article
R. Chen, L. Pan, C. Li, Y. Zhou, A. Chen
et al., "An improved deep fusion cnn for image recognition,"
Computers, Materials & Continua, vol. 65, no.2, pp. 1691–1706, 2020. https://doi.org/10.32604/cmc.2020.011706
Citations