Support Vector Data Description

By David Martinus Johannes Tax, Robert P. W. Duin. Machine-mediated learning, 2004

1,748 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/90902e16f4e8ff5e3c4bf0f971380af5753aacdd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. B. Liu
2. Geli Fei
3. Terrance E. Boult
4. Lei Shu
5. Bing Liu
6. Walter J. Scheirer
7. Hu Xu
8. Chunhua Shen

In Signal Processing

1. Terrance E. Boult
2. Lalit P. Jain
3. Guansong Pang
4. Chunhua Shen
5. Walter J. Scheirer
6. Richard Weber
7. Harry Wechsler
8. Marco Diani

Citations in the corpus

• Deep Anomaly Detection with Deviation Networks (2019, methodology): “resentations for the one-classifier, SVDD [27].”
• Cyberspace Security Using Adversarial Learning and Conformal Prediction (2015, background): “As both MTD and CCA have to cope with change and novelty detection, solutions built around zero-shot learning [70] using one-class SVM, are yet another possibility [71] [72], while the control strategy is to explore and exploit.”
• Breaking the Closed World Assumption in Text Classification (2016, background): “SVDD tries to place a hypersphere with the minimum radius around almost all the positive training points.”
• DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series (2019, methodology): “[21] B. Liu, Y. Xiao, L. Cao, Z. Hao, and F. Deng, ‘‘SVDD-based outlier detection on uncertain data,’’ Knowl.”
• Multi-class Open Set Recognition Using Probability of Inclusion (2014, positive): “A more sophisticated approach to accomplish the same goal is SVDD [49], where a hypersphere with the minimum radius is estimated around the positive class data that encompasses almost all training points.”
• Deep Learning for Anomaly Detection (2020, methodology): “as the problem of learning a description of a set of data instances to detect whether new instances conform to the training data or not. It is one of the most popular approaches for anomaly detection [103, 132, 140, 149]. Most one-class classification models are inspired by Support Vector Machines (”
• A tutorial overview of anomaly detection in hyperspectral images (2010, methodology): “is used. The SVDD [77, 78 ] is a one-class clas sifier”
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences (2020, background): “Bergman and Hoshen [4] combined this work with an SVDD type criterion and extended it to non-image data.”