Adversarially Learned One-Class Classifier for Novelty Detection (2018-02-25T00:00:00.000000Z)

TL;DR

The results on MNIST and Caltech-256 image datasets, along with the challenging UCSD Ped2 dataset for video anomaly detection illustrate that the proposed method learns the target class effectively and is superior to the baseline and state-of-the-art methods.

Abstract

Novelty detection is the process of identifying the observation(s) that differ in some respect from the training observations (the target class). In reality, the novelty class is often absent during training, poorly sampled or not well defined. Therefore, one-class classifiers can efficiently model such problems. However, due to the unavailability of data from the novelty class, training an end-to-end deep network is a cumbersome task. In this paper, inspired by the success of generative adversarial networks for training deep models in unsupervised and semi-supervised settings, we propose an end-to-end architecture for one-class classification. Our architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples. One network works as the novelty detector, while the other supports it by enhancing the inlier samples and distorting the outliers. The intuition is that the separability of the enhanced inliers and distorted outliers is much better than deciding on the original samples. The proposed framework applies to different related applications of anomaly and outlier detection in images and videos. The results on MNIST and Caltech-256 image datasets, along with the challenging UCSD Ped2 dataset for video anomaly detection illustrate that our proposed method learns the target class effectively and is superior to the baseline and state-of-the-art methods.

Authors

M. Sabokrou

5 papers

Mohammad Khalooei

1 papers

M. Fathy

2 papers

TL;DR

Abstract

Authors

References52 items

Fast and accurate detection and localization of abnormal behavior in crowded scenes

Abnormal event detection in videos using generative adversarial nets

Finding Anomalies with Generative Adversarial Networks for a Patrolbot

Wasserstein Generative Adversarial Networks

Incremental Kernel Null Space Discriminant Analysis for Novelty Detection

Image Denoising via CNNs: An Adversarial Approach

Training Adversarial Discriminators for Cross-Channel Abnormal Event Detection in Crowds

Provable Self-Representation Based Outlier Detection in a Union of Subspaces

Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Image-to-Image Translation with Conditional Adversarial Networks

Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis

Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes

Video anomaly detection and localisation based on the sparsity and reconstruction error of auto-encoder

Improved Techniques for Training GANs

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Learning Discriminative Reconstructions for Unsupervised Outlier Removal

Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Dual Principal Component Pursuit

Learning Deep Representations of Appearance and Motion for Anomalous Event Detection

Real-time anomaly detection and localization in crowded scenes

U-Net: Convolutional Networks for Biomedical Image Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

One-class classification: taxonomy of study and review of techniques

Multi-scale and real-time non-parametric approach for anomaly detection and localization

Robust Computation of Linear Models by Convex Relaxation

Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach

Sparse reconstruction cost for abnormal event detection

Robust PCA via Outlier Pursuit

Robust Subspace Segmentation by Low-Rank Representation

Anomaly detection in crowded scenes

Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates

Extracting and composing robust features with denoising autoencoders

Caltech-256 Object Category Dataset

One-Class Novelty Detection for Seizure Analysis from Intracranial EEG

Outlier Detection Using Random Walks

Pattern Recognition and Machine Learning

Detecting Irregularities in Images and in Video

A non-local algorithm for image denoising

Novelty detection: a review - part 1: statistical approaches

On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms

Anomaly Detection over Noisy Data using Learned Probability Distributions

LOF: identifying density-based local outliers

Network constraints and multi-objective optimization for one-class classification

GENERATIVE ADVERSARIAL NETS

Anomaly Detection and Localization in Crowded Scenes

Mnist handwritten digit database

Ucsd pedestrian dataset

Field of Study

Journal Information

Name

Page