Naive Gabor Networks

In this paper, we introduce naive Gabor Networks or Gabor-Nets which, for the first time in the literature, design and learn convolutional kernels strictly in the form of Gabor filters, aiming to reduce the number of parameters and constrain the solution space for convolutional neural networks (CNNs). In comparison with other Gabor-based methods, Gabor-Nets exploit the phase offset of the sinusoid harmonic to control the frequency characteristics of Gabor kernels, being able to adjust the convolutional kernels in accordance with the data from a frequency perspective. Furthermore, a fast 1-D decomposition of the Gabor kernel is implemented, bringing the original quadratic computational complexity of 2-D convolutions to a linear one. We evaluated our newly developed Gabor-Nets on two remotely sensed hyperspectral benchmarks, showing that our model architecture can significantly improve the convergence speed and the performance of CNNs, particularly when very limited training samples are available.

[1]  Gianluca Francini,et al.  Gabor filter based image representation for object classification , 2016, 2016 International Conference on Control, Decision and Information Technologies (CoDIT).

[2]  Ohad Shamir,et al.  Distribution-Specific Hardness of Learning Neural Networks , 2016, J. Mach. Learn. Res..

[3]  Antonio Plaza,et al.  A new deep convolutional neural network for fast hyperspectral image classification , 2017, ISPRS Journal of Photogrammetry and Remote Sensing.

[4]  Yuandong Tian,et al.  An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis , 2017, ICML.

[5]  Jianbo Su,et al.  Gabor Binary Layer in Convolutional Neural Networks , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[6]  Hu Yao,et al.  Gabor Feature Based Convolutional Neural Network for Object Recognition in Natural Scene , 2016, 2016 3rd International Conference on Information Science and Control Engineering (ICISCE).

[7]  Stephan J. Garbin,et al.  Harmonic Networks: Deep Translation and Rotation Equivariance , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  A. Calderon,et al.  Handwritten Digit Recognition using Convolutional Neural Networks and Gabor filters , 2003 .

[9]  Qian Du,et al.  Hyperspectral Image Classification Using Deep Pixel-Pair Features , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Nam Ik Cho,et al.  Age and gender classification using wide convolutional neural network and Gabor filter , 2018, 2018 International Workshop on Advanced Image Technology (IWAIT).

[11]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[12]  R. Porter,et al.  Robust rotation-invariant texture classification: wavelet, Gabor filter and GMRF based schemes , 1997 .

[13]  Zehang Sun,et al.  On-road vehicle detection using evolutionary Gabor filter optimization , 2005, IEEE Transactions on Intelligent Transportation Systems.

[14]  Qingquan Li,et al.  A 3-D Gabor Phase-Based Coding and Matching Framework for Hyperspectral Imagery Classification , 2018, IEEE Transactions on Cybernetics.

[15]  Prashant Parikh.  A Theory of Communication , 2010 .

[16]  Michael J. Lyons,et al.  Coding facial expressions with Gabor wavelets , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[17]  Heesung Kwon,et al.  Going Deeper With Contextual CNN for Hyperspectral Image Classification , 2016, IEEE Transactions on Image Processing.

[18]  Y. C. See,et al.  Investigation of face recognition using Gabor filter with random forest as learning framework , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[19]  Hongwei Liu,et al.  Deep Max-Margin Discriminant Projection , 2019, IEEE Transactions on Cybernetics.

[20]  Mehdi Chehel Amirani,et al.  Gabor Filter and Texture based Features for Palmprint Recognition , 2017, ICCS.

[21]  Kaushik Roy,et al.  Gabor filter assisted energy efficient fast learning Convolutional Neural Networks , 2017, 2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

[22]  Chen Chen,et al.  Gabor Convolutional Networks , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[23]  Ronald L. Rivest,et al.  Training a 3-node neural network is NP-complete , 1988, COLT '88.

[24]  Bing Liu,et al.  Supervised Deep Feature Extraction for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Hao Zhang,et al.  WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling , 2018, ICLR.

[26]  Yuandong Tian,et al.  Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima , 2017, ICML.

[27]  Nicolai Petkov,et al.  Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: bar and grating cells , 1997, Biological Cybernetics.

[28]  Lin Zhu,et al.  Hyperspectral Images Classification With Gabor Filtering and Convolutional Neural Network , 2017, IEEE Geoscience and Remote Sensing Letters.

[29]  D H HUBEL,et al.  RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE IN TWO NONSTRIATE VISUAL AREAS (18 AND 19) OF THE CAT. , 1965, Journal of neurophysiology.

[30]  Daniel A. Pollen,et al.  Visual cortical neurons as localized spatial frequency filters , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[31]  Rajiv Mehrotra,et al.  Edge detection models based on Gabor filters , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[32]  Tongwei Lu,et al.  Face recognition via Gabor and convolutional neural network , 2018, International Conference on Graphic and Image Processing.

[33]  Nelson Morgan,et al.  Robust CNN-based speech recognition with Gabor filter kernels , 2014, INTERSPEECH.

[34]  Maurice Weiler,et al.  Learning Steerable Filters for Rotation Equivariant CNNs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  Lianru Gao,et al.  Deep CNN With Multi-Scale Rotation Invariance Features for Ship Classification , 2018, IEEE Access.

[36]  Marc Acheroy,et al.  Texture classification using Gabor filters , 2002, Pattern Recognit. Lett..

[37]  Jun Li,et al.  Discriminative Low-Rank Gabor Filtering for Spectral–Spatial Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.