Gabor Convolutional Networks
Abstract
Steerable properties dominate the design of traditional filters, e.g., Gabor filters, and endow features the capability of dealing with spatial transformations. However, such excellent properties have not been well explored in the popular deep convolutional neural networks (DCNNs). In this paper, we propose a new deep model, termed Gabor Convolutional Networks (GCNs or Gabor CNNs), which incorporates Gabor filters into DCNNs to enhance the resistance of deep learned features to the orientation and scale changes. By only manipulating the basic element of DCNNs based on Gabor filters, i.e., the convolution operator, GCNs can be easily implemented and are compatible with any popular deep learning architecture. Experimental results demonstrate the super capability of our algorithm in recognizing objects, where the scale and rotation changes occur frequently. The proposed GCNs have much fewer learnable network parameters, and thus is easier to train with an endtoend pipeline. The source code will be here 1.
Publication Date
5-3-2018
Publication Title
Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
Volume
2018-January
Number of Pages
1254-1262
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/WACV.2018.00142
Copyright Status
Unknown
Socpus ID
85048226286 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85048226286
STARS Citation
Luan, Shangzhen; Zhang, Baochang; Zhou, Siyue; Chen, Chen; and Han, Jungong, "Gabor Convolutional Networks" (2018). Scopus Export 2015-2019. 8900.
https://stars.library.ucf.edu/scopus2015/8900