Robust Anomaly Detection in Images using Adversarial Autoencoders
Explore this paper's citation graph
Summary
It is found that continued training of autoencoders inevitably reduces the reconstruction error of outliers, and hence degrades the anomaly detection performance, and an adversarial autoencoder architecture is adapted, which imposes a prior distribution on the latent representation, typically placing anomalies into low likelihood-regions.
- Type
- preprint
- Published
- 2019-01-18
- Cited by
- 145
- References
- 25
- Access
- Open access
- OpenAlex
- https://openalex.org/W2909083954
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:58028959
Keywords
Autoencoder, Anomaly detection, Outlier, Artificial intelligence, Computer science
References
- A Novelty Detection Approach to Classification
- Auto-Encoding Variational Bayes
- Extracting and composing robust features with denoising autoencoders
- Identification of Outliers
- The Balanced Accuracy and Its Posterior Distribution
- A comparative study of RNN for outlier detection in data mining
- Gradient-based learning applied to document recognition
- Anomaly detection: A survey
- Estimating the Support of a High-Dimensional Distribution
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks
- High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning
- Deep Structured Energy Based Models for Anomaly Detection
- Detecting Adversarial Samples from Artifacts
- Sensitivity based robust learning for stacked autoencoder against evasion attack
- Anomaly Detection with Robust Deep Autoencoders
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Deep One-Class Classification
- Abnormality detection using deep neural networks with robust quasi-norm autoencoding and semi-supervised learning
- Adversarial autoencoders for novelty detection
Cited by
- Fence GAN: Towards Better Anomaly Detection
- Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
- Spatio-temporal adversarial learning for detecting unseen falls
- Structural Health Monitoring of Concrete Elements Using Deep Machine Learning
- Anomaly detection of solder joint on print circuit board by using Adversarial Autoencoder
- Monitoring Under-Modeled Rare Events for URLLC
- Misbehaviour Prediction for Autonomous Driving Systems
- Spectral Adversarial Feature Learning for Anomaly Detection in Hyperspectral Imagery
- Structural Health Monitoring of RC structures using optic fiber strain measurements: a deep learning approach
- Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
- Discriminative Reconstruction Constrained Generative Adversarial Network for Hyperspectral Anomaly Detection
- Exploring the Memorization-Generalization Continuum in Deep Learning
- Autoencoder and Adversarial-Learning-Based Semisupervised Background Estimation for Hyperspectral Anomaly Detection
- Adversarial autoencoder for detecting anomalies in soldered joints on printed circuit boards
- Modified Autoencoder Training and Scoring for Robust Unsupervised Anomaly Detection in Deep Learning
- Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error
- INFRASTRUCTURE DEGRADATION AND POST-DISASTER DAMAGE DETECTION USING ANOMALY DETECTING GENERATIVE ADVERSARIAL NETWORKS
- RVAE-ABFA : Robust Anomaly Detection for HighDimensional Data Using Variational Autoencoder
- Mixture of experts with convolutional and variational autoencoders for anomaly detection
- Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study
Related papers
- AEGR: a simple approach to gradient reversal in autoencoders for network anomaly detection
- Reconstruct Anomaly to Normal: Adversarial Learned and Latent Vector-constrained Autoencoder for Time-series Anomaly Detection
- Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
- Incorporating Decision-level Reconstruction Quality in Adversarial Autoencoders for Anomaly Detection
- Complementary Set Variational Autoencoder for Supervised Anomaly Detection
- MNGAN: Detecting Anomalies with Memorized Normal Patterns
- Unsupervised anomaly detection with LSTM autoencoders using statistical data-filtering
- Learning Not to Reconstruct Anomalies