Fast beta wavelet network-based feature extraction for image copy detection

ElAdel, Asma; Zaied, Mourad; Amar, Chokri Ben

doi:10.1016/j.neucom.2015.04.113

Cited by 7 publications

(2 citation statements)

References 34 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beta distribution often serves as a wavelet basis (De Oliveira & De Araújo, 2015) in computer vision applications (Amar et al, 2005;Jemai et al, 2010;ElAdel et al, 2016), but has not been utilized for mining graph data yet. Here we choose the Beta distribution as the graph kernel function and demonstrate that it meets the requirements of Hammond's graph wavelet.…”

Section: Beta Wavelet On Graphmentioning

confidence: 99%

Graph Neural Networks in Anomaly Detection

Wang

2022

Graph Neural Networks: Foundations, Frontiers, and Applications

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are widely applied for graph anomaly detection. As one of the key components for GNN design is to select a tailored spectral filter, we take the first step towards analyzing anomalies via the lens of the graph spectrum. Our crucial observation is the existence of anomalies will lead to the 'rightshift' phenomenon, that is, the spectral energy distribution concentrates less on low frequencies and more on high frequencies. This fact motivates us to propose the Beta Wavelet Graph Neural Network (BWGNN). Indeed, BWGNN has spectral and spatial localized band-pass filters to better handle the 'right-shift' phenomenon in anomalies. We demonstrate the effectiveness of BWGNN on four large-scale anomaly detection datasets. Our code and data are released at https://github.com/squareRoot3/ Rethinking-Anomaly-Detection.

show abstract

Section: Beta Wavelet On Graphmentioning

confidence: 99%

Graph Neural Networks in Anomaly Detection

Wang

2022

Graph Neural Networks: Foundations, Frontiers, and Applications

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithms built on neural network architectures have attracted interest as potential advances in the field of artificial intelligence [1]. The goal of neural networks is to solve the classification problem, which consists of correctly assigning a classification to a new observation based on a learned dataset containing observations for which the classification is known [2][3] [4]. Several studies have been conducted in recent years on how various machine learning algorithms, such as neural network learning algorithms, maintain data privacy [5] [6], as these techniques require access to private data.…”

Section: Introductionmentioning

confidence: 99%

B-CNN: Betadeep Convolutional Neural Network over encrypted data

Issaoui,

ElAdel,

ZAIED

2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

The results of automatic learning algorithms based on deep neural networks are impressive, and they are extensively used in a variety of fields. However, access to private information, frequently sensitive to confidentiality (financial, medical, etc.), is required in order to use them. This calls for good precision as well as special attention to the privacy and security of the data. In this paper, we propose a novel approach to solve this issue by using Convolutional Neural Network (CNN) model over encrypted data. In order to achieve our contribution, we focus on approximating the often used activation functions that seem to be the key functions in CNN networks which are: ReLu, Sigmoid and Tanh. We start by creating a low-degree polynomial, which is essential for a successful homomorphic encryption (HE). This polynomial which is based on Beta function and its primitive will be used as an activation function. The next step is to build a CNN model using batch normalization to ensure that the data are contained inside a limited interval. Finally, MNIST is used in order to evaluate our methodology and assess the effectiveness of the proposed approach. The experimental results support the efficacy of the proposed approach.

show abstract