Advanced search
Start date
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Image classification in frequency domain with 2SReLU: A second harmonics superposition activation function

Full text
Watanabe, Thomio [1] ; Wolf, Denis F. [1]
Total Authors: 2
[1] Univ Sao Paulo, Inst Math & Comp Sci, Sao Paulo - Brazil
Total Affiliations: 1
Document type: Journal article
Source: APPLIED SOFT COMPUTING; v. 112, NOV 2021.
Web of Science Citations: 0

Deep Convolutional Neural Networks are able to identify complex patterns and perform tasks with super-human capabilities. However, besides the exceptional results, they are not completely understood and it is still impractical to hand-engineer similar solutions. In this work, an image classification Convolutional Neural Network and its building blocks are described from a frequency domain perspective. Some network layers have established counterparts in the frequency domain like the convolutional and pooling layers. We propose the 2SReLU layer, a novel non-linear activation function that preserves high frequency components in deep networks. A convolution-free network is presented, and it is demonstrated that in the frequency domain it is possible to achieve competitive results without using the computationally costly convolution operation. A source code implementation in PyTorch is provided at: (C) 2021 Elsevier B.V. All rights reserved. (AU)

FAPESP's process: 15/26293-0 - Autonomous vehicles multi obstacle tracking with sensor fusion.
Grantee:Thomio Watanabe
Support Opportunities: Scholarships in Brazil - Doctorate