Gabor Convolutional Networks

Shangzhen Luan, Chen Chen, Baochang Zhang, Jungong Han, Jianzhuang Liu

Research output: Contribution to journalArticlepeer-review

251 Citations (SciVal)

Abstract

In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of “basis filters.” Steerable properties dominate the design of the traditional filters, e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely, Gabor convolutional networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework, and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang.
Original languageEnglish
Pages (from-to)4357-4366
Number of pages10
JournalIEEE Transactions on Image Processing
Volume27
Issue number9
Early online date10 May 2018
DOIs
Publication statusPublished - 30 Sept 2018
Externally publishedYes

Keywords

  • Gabor CNNs
  • Gabor filters
  • convolutional neural networks
  • kernel modulation
  • orientation

Fingerprint

Dive into the research topics of 'Gabor Convolutional Networks'. Together they form a unique fingerprint.

Cite this