The Importance of the Instantaneous Phase for classification using Convolutional Neural Networks

2022-07-01 · Luis Sanchez Tapia, Marios S. Pattichis, Sylvia Celedon-Pattichis, Carlos Lopez Leiva

Large-scale training of Convolutional Neural Networks (CNN) is extremely demanding in terms of computational resources. Also, for specific applications, the standard use of transfer learning also tends to require far more resources than what may be needed. This work examines the impact of using AM-FM representations as input images for CNN classification applications. A comparison was made between AM-FM components combinations and grayscale images as inputs for reduced and complete networks. The results showed that only the phase component produced significant predictions within a simple network. Neither IA or gray scale image were able to induce any learning in the system. Furthermore, the FM results were 7x faster during training and used 123x less parameters compared to state-of-the-art MobileNetV2 architecture, while maintaining comparable performance (AUC of 0.78 vs 0.79).

📄 PDF Abstract BibTeX arXiv:2207.00672

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Batch Normalization 설명 없음

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …

Average Pooling 설명 없음

Inverted Residual Block 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

The Importance of the Instantaneous Phase in Detecting Faces with Convolutional Neural Networks

2022-08-03 · Luis Sanchez Tapia

Convolutional Neural Networks (CNN) have provided new and accurate methods for processing digital images and videos. Yet, training CNNs is extremely demanding in terms of computational resources. Also, for specific appli…

Face Detection Transfer Learning

Classification of Intra-Pulse Modulation of Radar Signals by Feature Fusion Based Convolutional Neural Networks

2022-05-19 · Fatih Cagatay Akyon, Yasar Kemal Alp, Gokhan Gok, Orhan Arikan

Detection and classification of radars based on pulses they transmit is an important application in electronic warfare systems. In this work, we propose a novel deep-learning based technique that automatically recognizes…

Learning audio representations via phase prediction

2019-10-25 · Félix de Chaumont Quitry, Marco Tagliasacchi, Dominik Roblek

We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the m…

Decoder Prediction Self-Supervised Learning

Cerebral Signal Instantaneous Parameters Estimation MATLAB Toolbox - User Guide Version 2.3

2016-10-07 · Esmaeil Seraj

This document is meant to help individuals use the Cerebral Signal Phase Analysis toolbox which implements different methods for estimating the instantaneous phase and frequency of a signal and calculating some related p…

EEG Electroencephalogram (EEG)

Modeling Fission Gas Release at the Mesoscale using Multiscale DenseNet Regression with Attention Mechanism and Inception Blocks

2023-10-12 · Peter Toma, Md Ali Muntaha, Joel B. Harley, Michael R. Tonks

Mesoscale simulations of fission gas release (FGR) in nuclear fuel provide a powerful tool for understanding how microstructure evolution impacts FGR, but they are computationally intensive. In this study, we present an …