Consistency-based anomaly detection with adaptive multiple-hypotheses predictions

10/31/2018
by   Duc Tam Nguyen, et al.
0

In out-of-distribution classification tasks, only some classes - the normal cases - can be modeled with data, whereas the variation of all possible anomalies is too large to be described sufficiently by samples. Thus, the wide-spread discriminative approaches cannot cover such learning tasks and rather generative models, which attempt to learn the input density of the ordinary cases, are used. However, generative models suffer under a large input dimensionality (as in images) and are typically inefficient learners. Motivated by the Local-Outlier-Factor (LOF) method, in this work, we propose to allow the network to directly estimate the local density functions since, for the detection of outliers, the local neighborhood is more important than the global one. At the same time, we retain consistency in the sense that the model must not support areas of the input space that are not covered by samples. Our method allows the model to identify out-of-distribution samples reliably. For the anomaly detection task on CIFAR-10, our ConAD model results in up to 5 points improvement over previously reported results.

READ FULL TEXT
research
10/31/2018

Anomaly DetectionWith Multiple-Hypotheses Predictions

In one-class-learning tasks, only the normal case (foreground) can be mo...
research
10/02/2018

Generative Ensembles for Robust Anomaly Detection

Deep generative models are capable of learning probability distributions...
research
12/07/2020

Perfect density models cannot guarantee anomaly detection

Thanks to the tractability of their likelihood, some deep generative mod...
research
05/24/2021

Deep Visual Anomaly detection with Negative Learning

With the increase in the learning capability of deep convolution-based a...
research
07/23/2023

TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models

Tables are an abundant form of data with use cases across all scientific...
research
05/24/2023

Real time dense anomaly detection by learning on synthetic negative data

Most approaches to dense anomaly detection rely on generative modeling o...
research
06/27/2023

Anomaly Detection in Networks via Score-Based Generative Models

Node outlier detection in attributed graphs is a challenging problem for...

Please sign up or login with your details

Forgot password? Click here to reset