2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDTEC-6.3
Paper Title TAYLOR SERIES KERNELIZED LAYER FOR FINE-GRAINED RECOGNITION
Authors Mohamed Amine Mahmoudi, Mustapha Stambouli University of Mascara, Algeria; Aladine Chetouani, Laboratoire PRISME, Université d'Orléans, France; Fatma Boufera, Mustapha Stambouli University of Mascara, Algeria; Hedi Tabia, IBISC laboratory, University of Paris-Saclay, Paris, France
SessionTEC-6: Image and Video Processing 2
LocationArea G
Session Time:Monday, 20 September, 15:30 - 17:00
Presentation Time:Monday, 20 September, 15:30 - 17:00
Presentation Poster
Topic Image and Video Processing: Linear and nonlinear filtering of images & video
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract In this paper, we propose a new architecture to enhance dense layers with a Taylor Series Kernelized Layer (TSKL). The proposed layer expands the underlying linear kernel of dense layers to a higher-order Taylor series kernel. This kernel is able to learn more complex patterns than the linear one and thus be more discriminative. In other words, TKSL first maps input data to a higher-dimensional Reproducing Kernel Hilbert Space (RKHS). After that, it learns a linear classifier in that RKHS which corresponds to a powerful non-linear classifier in the original feature space. The mapping features to a higher-order RKHS is performed implicitly by leveraging the kernel trick and explicitly by combining multiple kernels. The experimental results demonstrate that the proposed layer outperforms the ordinary dense layer when uses in both Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs).