CoChat
Sign Up
Cited by 428Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesImage Retrieval and Classification Techniques

Gabor convolutional networks

Open access
Luan, Shangzhen, Chen, Chen, Zhang, Baochang, Han, Jungong, Liu, Jianzhuang·2018·IEEE Transactions on Image Processing
DOI 10.1109/tip.2018.2835143
Open this paper in CoChat — free accountOpen PDF

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tip.2018.2835143

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Convolutional filters in CNNs often converge to Gabor functions.

    “but also from the fact that convolutional filters in CNNs often converge to Gabor functions [107].”

    From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [107]

    In A. Motivation (p. 2), the paper says many learned filters in the first convolutional layer of an AlexNet example are similar to Gabor filters. That supports the resemblance, but it does not establish that CNN filters generally converge to Gabor functions. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • The GNN model presented a reduction factor of four with respect to the number of parameters needed for the other methods.

    “Furthermore, the proposed model presented a reduction factor of four with respect to the number of parameters needed for the other methods.”

    From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [107]

    In A. MNIST (p. 6), the paper reports a GCN configuration using one-quarter as many parameters as baseline CNNs. The claim extends that fourfold reduction to “the other methods” generally, but Table III (p. 7) shows varying parameter counts, including an ORN configuration with the same count as a GCN configuration. The paper calls its model GCN, not GNN. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • On the DSTG dataset, GNNs presented a better performance, with an average precision of 79.93%, than other state-of-the-art models such as R-CNN, Fast R-CNN, Faster R-CNN, YOLOv3, Tiny YOLOv3, and SSD300, which obtained average precision metrics varying from 9.41% to 72.76%.

    “On that dataset, GNNs presented a better performance, with an average precision (AP) of 79.93%, than other state-of-the-art models, such as R-CNN, Fast R-CNN, Faster R-CNN, YOLOv3, Tiny YOLOv3 and SSD300, obtaining average precision metrics that varied from 9.41% to 72.76%.”

    From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [107]

    Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 35

  1. [1][1] Y.-L. Boureau, J. Ponce, and Y. LeCun, 'A theoretical analysis of feature pooling in visual recognition,' in Proc. 27th Int. Conf. Mach. Learn. (ICML) , 2010, pp. 111-118. -
  2. [2][2] Y. Zhou, Q. Ye, Q. Qiu, and J. Jiao, 'Oriented response networks,' in Proc. Int. Conf. Comput. Vis. Pattern Recognit. , Jul. 2017, pp. 4961-4970. -
  3. [4][4] R. Girshick, 'Fast R-CNN,' in Proc. IEEE Int. Conf. Comput. Vis. , Dec. 2015, pp. 1440-1448. -
  4. [5][5] S. Ji, W. Xu, M. Yang, and K. Yu, '3D convolutional neural networks for human action recognition,' IEEE Trans. Pattern Anal. Mach. Intell. , vol. 35, no. 1, pp. 221-231, Jan. 2013. -
  5. [6][6] J.-H. Jacobsen, J. van Gemert, Z. Lou, and A. W. M. Smeulders, 'Structured receptive fields in CNNs,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , Jun. 2016, pp. 2610-2619. -
  6. [8][8] H. Yao, L. Chuyi, H. Dan, and Y. Weiyu, 'Gabor feature based convolutional neural network for object recognition in natural scene,' in Proc. Int. Conf. Inf. Sci. Control Eng. , Jul. 2016, pp. 386-390. -
  7. [9][9] S. S. Sarwar, P. Panda, and K. Roy, 'Gabor filter assisted energy efficient fast learning convolutional neural networks,' in Proc. IEEE/ACM Int. Symp. Low Power Electron. Des. , Jul. 2017, pp. 1-6. -
  8. [10][10] J. Han, D. Zhang, X. Hu, L. Guo, J. Ren, and F. Wu, 'Background prior-based salient object detection via deep reconstruction residual,' IEEE Trans. Circuits Syst. Video Technol. , vol. 25, no. 8, pp. 1309-1321, Aug. 2015. -
  9. [11][11] Y. Yan et al. , 'Unsupervised image saliency detection with gestaltlaws guided optimization and visual attention based refinement,' Pattern Recognit. , vol. 79, pp. 65-78, Jul. 2018. -
  10. [12][12] Z. Wang, J. Ren, D. Zhang, M. Sun, and J. Jiang, 'A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos,' Neurocomputing , vol. 287, pp. 68-83, Apr. 2018. -
  11. [14][14] S. Luan et al. , 'Gabor convolutional networks,' in Proc. WACV , 2018, pp. 1254-1262. -
  12. [15][15] D. Gabor, 'Theory of communication. Part 1: The analysis of information,' J. Inst. Elect. Eng.-III, Radio Commun. Eng. , vol. 93, no. 26, pp. 429-441, Jul. 1946. -
  13. [16][16] B. Zhang, Y. Gao, S. Zhao, and J. Liu, 'Local derivative pattern versus local binary pattern: Face recognition with high-order local pattern descriptor,' IEEE Trans. Image Process. , vol. 19, no. 2, pp. 533-544, Feb. 2010. -
  14. [17][17] D. A. Van Dyk and X.-L. Meng, 'The art of data augmentation,' J. Comput. Graph. Statist. , vol. 10, no. 1, pp. 1-50, 2001. -
  15. [18][18] D. Laptev, N. Savinov, J. M. Buhmann, and M. Pollefeys, 'TI-POOLING: Transformation-invariant pooling for feature learning in convolutional neural networks,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , Jun. 2016, pp. 289-297. -
  16. [19][19] M. Jaderberg, K. Simonyan, A. Zisserman, and K. Kavukcuoglu, 'Spatial transformer networks,' in Proc. Adv. Neural Inf. Process. Syst. , 2015, pp. 2017-2025. -
  17. [20][20] J. Bruna and S. Mallat, 'Invariant scattering convolution networks,' IEEE Trans. Pattern Anal. Mach. Intell. , vol. 35, no. 8, pp. 1872-1886, Aug. 2013. -
  18. [21][21] L. Sifre and S. Mallat, 'Rotation, scaling and deformation invariant scattering for texture discrimination,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , Jun. 2013, pp. 1233-1240. -
  19. [22][22] B. Kwolek, Face Detection Using Convolutional Neural Networks and Gabor Filters . Berlin, Germany: Springer, 2005. -
  20. [23][23] A. Calderón, S. Roa, and J. Victorino, 'Handwritten digit recognition using convolutional neural networks and Gabor filters,' in Proc. Int. Congr. Comput. Intell. , 2003. -
  21. [24][24] S.-Y. Chang and N. Morgan, 'Robust CNN-based speech recognition with Gabor filter kernels,' in Proc. 15th Annu. Conf. Int. Speech Commun. Assoc. , 2014, pp. 905-909. -
  22. [26][26] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, 'Gradient-based learning applied to document recognition,' Proc. IEEE , vol. 86, no. 11, pp. 2278-2324, Nov. 1998. -
  23. [27][27] Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, 'Reading digits in natural images with unsupervised feature learning,' in Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn. , 2011, p. 5. -
  24. [29][29] J. Deng, W. Dong, R. Socher, and L. J. Li, 'ImageNet: A large-scale hierarchical image database,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) , Jun. 2009, pp. 248-255. -
  25. [30][30] L. Bossard, M. Guillaumin, and L. Van Gool, 'Food-101-Mining discriminative components with random forests,' in Proc. Eur. Conf. Comput. Vis. , 2014, pp. 446-461. -
  26. [32][32] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. (2012). 'Improving neural networks by preventing co-adaptation of feature detectors.' [Online]. Available: https://arxiv.org/abs/1207.0580 - · arXiv
  27. [34][34] K. Simonyan and A. Zisserman. (2014). 'Very deep convolutional networks for large-scale image recognition.' [Online]. Available: https://arxiv.org/abs/1409.1556 - · arXiv
  28. [35][35] M. Lin, Q. Chen, and S. Yan, 'Network in network,' in Proc. ICLR , 2014, pp. 1-32. -
  29. [36][36] F. Juefei-Xu, V. N. Boddeti, and M. Savvides. (2016). 'Local binary convolutional neural networks.' [Online]. Available: https://arxiv.org/abs/1608.06049 - · arXiv
  30. [38][38] Y. Cui, F. Zhou, J. Wang, X. Liu, Y. Lin, and S. Belongie, 'Kernel pooling for convolutional neural networks,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , Jul. 2017, pp. 3049-3058. -
  31. [39][39] Y. Gao, O. Beijbom, N. Zhang, and T. Darrell, 'Compact bilinear pooling,' in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. , Jun. 2017, pp. 317-326. -
  32. [40][40] B. Zhang, Y. Yang, C. Chen, L. Yang, J. Han, and L. Shao, 'Action recognition using 3D histograms of texture and a multi-class boosting classifier,' IEEE Trans. Image Process. , vol. 26, no. 10, pp. 4648-4660, Oct. 2017. -
  33. [41][41] B. Zhang et al. , 'Latent constrained correlation filter,' IEEE Trans. Image Process. , vol. 27, no. 3, pp. 1038-1048, Mar. 2018. -
  34. [42][42] B. Zhang et al. , 'One-two-one networks for compression artifacts reduction in remote sensing,' ISPRS J. Photogramm. Remote Sens. , to be published, doi: 10.1016/j.isprsjprs.2018.01.003. - · DOI
  35. [43][43] B. Zhang, A. Perina, Z. Li, V. Murino, J. Liu, and R. Ji, 'Bounding multiple Gaussians uncertainty with application to object tracking,' Int. J. Comput. Vis. , vol. 118, no. 3, pp. 364-379, 2016. Shangzhen Luan received the B.S. and master's degrees from the Department of Automation Science and Electrical Engineering, Beihang University. His current research interests include signal and image processing, pattern recognition, and computer vision. Chen Chen received the B.E. degree in automation from Beijing Forestry University, Beijing, China, in 2009, the M.S. degree in electrical engineering from Mississippi State University, Starkville, MS, USA, in 2012, and the Ph.D. degree from The University of Texas at Dallas, Richardson, TX, USA, in 2016. He is currently a Post-Doctoral Fellow with the Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA. His current research interests include compressed sensing, signal and image processing, pattern recognition, and computer vision. He has authored or co-authored over 40 papers in refereed journals and conferences in these areas. Baochang Zhang received the B.S., M.S., and Ph.D. degrees in computer science from the Harbin Institute of the Technology, Harbin, China, in 1999, 2001, and 2006, respectively. From 2006 to 2008, he was a Research Fellow with The Chinese University of Hong Kong, Hong Kong, and also with Griffith University, Brisban, Australia. He is currently an Associate Professor with Beihang University, Beijing, China. His current research interests include pattern recognition, machine learning, face recognition, and wavelets. Jungong Han was a Senior Scientist with Civolution Technology (a combining synergy of Philips CI and Thomson STS) from 2012 to 2015, a Research Staff with the Centre for Mathematics and Computer Science from 2010 to 2012, and a Researcher with the Technical University of Eindhoven, The Netherlands, from 2005 to 2010. He is currently a Senior Lecturer with the Department of Computer Science, Northumbria University, U.K. Jianzhuang Liu received the Ph.D. degree in computer vision from The Chinese University of Hong Kong, Hong Kong, in 1997. From 1998 to 2000, he was a Research Fellow with Nanyang Technological University, Singapore. From 2000 to 2012, he was a Post-Doctoral Fellow, an Assistant Professor, and an Adjunct Associate Professor with The Chinese University of Hong Kong. In 2011, he joined the Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, as a Professor. He is currently a Principal Researcher with Huawei Technologies Company, Ltd., Shenzhen. He has authored over 150 papers. His research interests include computer vision, image processing, machine learning, multimedia, and graphics.

Cited by

Sorted by citations

Authors
Luan, S., Chen, C., Zhang, B., Han, J., & Liu, J.
Affiliations
  • Beihang University (CN)
  • University of North Carolina at Charlotte (US)
  • Lancaster University (GB)
  • Huawei Technologies (China) (CN)
ORCID
Venue
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2018-09
Volume
27
Issue
9
Pages
4357-4366
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
DOI
10.1109/tip.2018.2835143
OpenAlex
W2610691757
Cited by
428
References
6
Citations by year
2026: 32 · 2025: 58 · 2024: 42 · 2023: 47 · 2022: 53 · 2021: 66 · 2020: 49 · 2019: 52 · 2018: 27 · 2017: 2
FWCI
24.26
Type
journal article
Language
en
Open access
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)
Locations
  • IEEE Transactions on Image Processing (publishedVersion)
  • PubMed (publishedVersion)
  • Lancaster EPrints (Lancaster University) (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Warwick Research Archive Portal (University of Warwick) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Natural Science Foundation of China (61672079, 61473086)
  • Shenzhen Peacock Plan (KQTD2016112515134654)
  • Open Projects Program of National Laboratory of Pattern Recognition
  • National Basic Research Program of China (2015CB352501)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
Keywords
Gabor filters, steerable filters, orientation invariance, scale invariance, rotation invariance, object recognition, feature representation, convolution operators

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review