On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques

• URL: http://arxiv.org/abs/2403.15497v1
• Date: Thu, 21 Mar 2024 18:31:47 GMT
• Title: On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques
• Authors: Laura O'Mahony, David JP O'Sullivan, Nikola S. Nikolov,
• Abstract summary: We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. In many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data.
• Score: 0.6554326244334868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.

Related papers

• ADer: A Comprehensive Benchmark for Multi-class Visual Anomaly Detection [52.228708947607636]
  This paper proposes a comprehensive visual anomaly detection benchmark, textbftextitADer, which is a modular framework for new anomaly detection methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. We objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection.
  arXiv  Detail & Related papers  (2024-06-05T13:40:07Z)
• Anomaly Detection by Context Contrasting [57.695202846009714]
  Anomaly Detection focuses on identifying samples that deviate from the norm. Recent advances in self-supervised learning have shown great promise in this regard. We propose Con2, which addresses this problem by setting normal training data into distinct contexts. Our approach achieves state-of-the-art performance on various benchmarks while exhibiting superior performance in a more realistic healthcare setting.
  arXiv  Detail & Related papers  (2024-05-29T07:59:06Z)
• A Critical Review of Common Log Data Sets Used for Evaluation of Sequence-based Anomaly Detection Techniques [2.5339493426758906]
  We analyze six publicly available log data sets with focus on the manifestations of anomalies and simple techniques for their detection. Our findings suggest that most anomalies are not directly related to sequential manifestations and that advanced detection techniques are not required to achieve high detection rates on these data sets.
  arXiv  Detail & Related papers  (2023-09-06T09:31:17Z)
• WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining [0.6754597324022876]
  Outlier detection can reveal vital information about system faults, fraudulent activities, and patterns in the data. This article proposed the WePaMaDM-Outlier Detection with distinct mass data mining domain. It also investigates the significance of data modeling in outlier detection techniques in surveillance, fault detection, and trend analysis.
  arXiv  Detail & Related papers  (2023-06-09T07:00:00Z)
• An Outlier Exposure Approach to Improve Visual Anomaly Detection Performance for Mobile Robots [76.36017224414523]
  We consider the problem of building visual anomaly detection systems for mobile robots. Standard anomaly detection models are trained using large datasets composed only of non-anomalous data. We tackle the problem of exploiting these data to improve the performance of a Real-NVP anomaly detection model.
  arXiv  Detail & Related papers  (2022-09-20T15:18:13Z)
• Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability [21.98595908296989]
  We demonstrate that the performance of state-of-the-art anomaly detection methods is degraded substantially by adding only small adversarial perturbations to the sensor data. We use different scoring metrics such as prediction errors, anomaly, and classification scores over several public and private datasets. We demonstrate, for the first time, the vulnerabilities of anomaly detection systems against adversarial attacks.
  arXiv  Detail & Related papers  (2022-08-24T01:55:50Z)
• Context-Aware Drift Detection [0.0]
  Two-sample tests of homogeneity form the foundation upon which existing approaches to drift detection build. We develop a more general drift detection framework built upon a foundation of two-sample tests for conditional distributional treatment effects.
  arXiv  Detail & Related papers  (2022-03-16T14:23:02Z)
• DAE : Discriminatory Auto-Encoder for multivariate time-series anomaly detection in air transportation [68.8204255655161]
  We propose a novel anomaly detection model called Discriminatory Auto-Encoder (DAE) It uses the baseline of a regular LSTM-based auto-encoder but with several decoders, each getting data of a specific flight phase. Results show that the DAE achieves better results in both accuracy and speed of detection.
  arXiv  Detail & Related papers  (2021-09-08T14:07:55Z)
• Deep Visual Anomaly detection with Negative Learning [18.79849041106952]
  In this paper, we propose anomaly detection with negative learning (ADNL), which employs the negative learning concept for the enhancement of anomaly detection. The idea is to limit the reconstruction capability of a generative model using the given a small amount of anomaly examples. This way, the network not only learns to reconstruct normal data but also encloses the normal distribution far from the possible distribution of anomalies.
  arXiv  Detail & Related papers  (2021-05-24T01:48:44Z)
• Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models [59.04636530383049]
  Anomalies or failures in large computer systems, such as the cloud, have an impact on a large number of users. We propose a framework for anomaly detection in log data, as a major troubleshooting source of system information.
  arXiv  Detail & Related papers  (2021-02-23T09:17:05Z)
• Graph Embedding with Data Uncertainty [113.39838145450007]
  spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. Most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty.
  arXiv  Detail & Related papers  (2020-09-01T15:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.