Deep One-Class Classification
Explore this paper's citation graph
Summary
This paper introduces a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective and shows the effectiveness of the method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GT-SRB stop signs.
- Type
- article
- Published
- 2018-07-03
- Cited by
- 2,784
- References
- 59
- OpenAlex
- https://openalex.org/W2803697594
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:49312162
Keywords
Class (philosophy), Artificial intelligence, Computer science
References
- Understanding the difficulty of training deep feedforward neural networks
- One-class classifier networks for target recognition applications
- Auto-Encoding Variational Bayes
- Theory of Reproducing Kernels.
- Extracting and composing robust features with denoising autoencoders
- On nonparametric estimation of density level sets
- Deep learning in neural networks: An overview
- Generalized RBF feature maps for Efficient Detection
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition
- On Estimation of a Probability Density Function and Mode
- Anomaly detection: A survey
- Sensor fault and patient anomaly detection and classification in medical wireless sensor networks
- Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction
- Estimating the Support of a High-Dimensional Distribution
- Anomaly-based network intrusion detection: Techniques, systems and challenges
- LOF: identifying density-based local outliers
- Random Features for Large-Scale Kernel Machines
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Feature Selection for Classification of Hyperspectral Data by SVM
- ImageNet classification with deep convolutional neural networks
Cited by
- Clustering With Outlier Removal
- Learning Deep Features for One-Class Classification
- Anomaly Detection using One-Class Neural Networks
- Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
- Learning Neural Random Fields with Inclusive Auxiliary Generators
- Image Anomalies: A Review and Synthesis of Detection Methods
- Frequentist uncertainty estimates for deep learning
- Consistency-based anomaly detection with adaptive multiple-hypotheses predictions
- Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study
- One-Class Feature Learning Using Intra-Class Splitting
- Unsupervised Learning of the Set of Local Maxima
- Robust Anomaly Detection in Images using Adversarial Autoencoders
- Deep One-Class Classification Using Data Splitting
- Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning
- The Future Agricultural Biogas Plant in Germany: A Vision
- Difference-Seeking Generative Adversarial Network
- Novelty Detection for Person Re-identification in an Open World
- Deep One-Class Classification Using Intra-Class Splitting
- The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation
- Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection
Related papers
- Learning Multiple Layers of Features from Tiny Images
- Deep Anomaly Detection Using Geometric Transformations
- Latent Space Autoregression for Novelty Detection
- Deep Learning for Anomaly Detection: A Survey
- Anomaly Detection using One-Class Neural Networks
- Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection