Gabor Convolutional Networks

Abstract

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 .

Expression of Concern: Facial feature discovery for ethnicity recognition

“…Based on scale, illumination and pose, Yan and Zhang () used PCA to analyze the facial features on CMU and UCSD databases. Recently, many deep neural network methods are also used for face analysis and recognition (Chen, Zhang, Dong, Le, & Rao, ; Luan et al, ; Trigeorgis, Snape, Kokkinos, & Zafeiriou, ; Zhang, Song, & Qi, ). Srinivas et al () focused on predicting ethnicity using a convolutional neural network (CNN) with the Wild East Asian Face Dataset.…”

Classification of stomach infections: A paradigm of convolutional neural network along with classical features fusion and selection

“…The performance of Gabor features is increased after fusion with deep CNN features (Shi et al, ). Different studies (Chen et al, ; Kwolek, ; Luan, Chen, Zhang, Han, & Liu, ; Yao, Chuyi, Dan, & Weiyu, ) have highlighted the advantages of fusion of both these features. Therefore, in this work, CNN features are combined with color and statistical descriptors (DCT and DWT).…”

Rotation Invariant Local Binary Convolution Neural Networks

“…Instead of introducing extra functional modules or new network topology, most recent studies [38,28] implement the prior knowledge of rotation to the most basic element of DCNNs, i.e., the convolution operator. [38] introduced Actively Rotating Filters (ARFs) to generate feature maps which encode the location and orientation information.…”

“…[38] introduced Actively Rotating Filters (ARFs) to generate feature maps which encode the location and orientation information. In [28], they incorporated conventional Gabor filters into DC-NNs to enhance the resistance of learned features to the orientation and scale changes. Both the ORNs and GCNs can be naturally fused with any popular deep learning architecture, as well as latest techniques(BatchNorm, ReLu).…”