Vacant Holes for Unsupervised Detection of the Outliers in Compact Latent Representation
Detection of the outliers is pivotal for any machine learning model deployed and operated in real-world. It is essential for the Deep Neural Networks that were shown to be overconfident with such inputs. Moreover, even deep generative models that allow estimation of the probability density of the input fail in achieving this task. In this work, we concentrate on the specific type of these models: Variational Autoencoders (VAEs). First, we unveil a significant theoretical flaw in the assumption of the classical VAE model. Second, we enforce an accommodating topological property to the image of the deep neural mapping to the latent space: compactness to alleviate the flaw and obtain the means to provably bound the image within the determined limits by squeezing both inliers and outliers together. We enforce compactness using two approaches: (i) Alexandroff extension and (ii) fixed Lipschitz continuity constant on the mapping of the encoder of the VAEs. Finally and most importantly, we discover that the anomalous inputs predominantly tend to land on the vacant latent holes within the compact space, enabling their successful identification. For that reason, we introduce a specifically devised score for hole detection and evaluate the solution against several baseline benchmarks achieving promising results.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On Variational Learning of Controllable Representations for Text without Supervision
The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space. However, on discrete data such as …
Style TransferText GenerationText Style TransferFocus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization
The essence of unsupervised anomaly detection is to learn the compact distribution of normal samples and detect outliers as anomalies in testing. Meanwhile, the anomalies in real-world are usually subtle and fine-grained…
Anomaly DetectionContrastive LearningUnsupervised Anomaly DetectionDetection of Small Holes by the Scale-Invariant Robust Density-Aware Distance (RDAD) Filtration
A novel topological-data-analytical (TDA) method is proposed to distinguish, from noise, small holes surrounded by high-density regions of a probability density function. The proposed method is robust against additive no…
Density EstimationLotRec: A Recommender for Urban Vacant Lot Conversion
Vacant lots are neglected properties in a city that lead to environmental hazards and poor standard of living for the community. Thus, reclaiming vacant lots and putting them to productive use is an important considerati…
Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Data
Benchmarking unsupervised outlier detection is difficult. Outliers are rare, and existing benchmark data contains outliers with various and unknown characteristics. Fully synthetic data usually consists of outliers and r…
BenchmarkingOutlier Detection