Suppressing Outlier Reconstruction in Autoencoders for Out-of-Distribution Detection
While only trained to reconstruct training data, autoencoders may produce high-quality reconstructions of inputs that are well outside the training data distribution. This phenomenon, which we refer to as outlier reconstruction, has a detrimental effect on the use of autoencoders for outlier detection, as an autoencoder will misclassify a clear outlier as being in-distribution. In this paper, we introduce the Energy-Based Autoencoder (EBAE), an autoencoder that is considerably less susceptible to outlier reconstruction. The core idea of EBAE is to treat the reconstruction error as an energy function of a normalized density and to strictly enforce the normalization constraint. We show that the reconstruction of non-training inputs can be suppressed, and the reconstruction error made highly discriminative to outliers, by enforcing this constraint. We empirically show that EBAE significantly outperforms both existing autoencoders and other generative models for several out-of-distribution detection tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Outlier DetectionOut-of-Distribution DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Autoencoding Under Normalization Constraints
Likelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maxi…
Outlier DetectionVersatile Anomaly Detection with Outlier Preserving Distribution Mapping Autoencoders
State-of-the-art deep learning methods for outlier detection make the assumption that anomalies will appear far away from inlier data in the latent space produced by distribution mapping deep networks. However, this ass…
Anomaly DetectionOutlier DetectionRobust Anomaly Detection in Images using Adversarial Autoencoders
Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal …
Anomaly DetectionMedical Image AnalysisOutlier Preserving Distribution Mapping Autoencoders
State-of-the-art deep outlier detection methods map data into a latent space with the aim of having outliers far away from inliers in this space. Unfortunately, this often fails as the divergence penalty they adopt pus…
Outlier DetectionLearning low-dimensional manifolds under the L0-norm constraint for unsupervised outlier detection
Unsupervised outlier detection without the need for clean data has attracted great attention because it is suitable for real-world problems as a result of its low data collection costs. Reconstruction-based methods are p…
Outlier Detection