Related papers: Position: Untrained Machine Learning for Anomaly Detection

Position: Untrained Machine Learning for Anomaly Detection

URL: http://arxiv.org/abs/2502.03876v1
Date: Thu, 06 Feb 2025 08:46:59 GMT
Title: Position: Untrained Machine Learning for Anomaly Detection
Authors: Juan Du, Dongheng Chen, Hao Yan,
Abstract summary: Untrained anomaly detection based on only one sample is an emerging research problem motivated by real manufacturing industries. This paper aims to provide a formal definition of untrained anomaly detection problem based on 3D point cloud data.
Score: 9.82563728949843
License:
Abstract: Anomaly detection based on 3D point cloud data is an important research problem and receives more and more attention recently. Untrained anomaly detection based on only one sample is an emerging research problem motivated by real manufacturing industries such as personalized manufacturing that only one sample can be collected without any additional labels. How to accurately identify anomalies based on one 3D point cloud sample is a critical challenge in both industrial applications and the field of machine learning. This paper aims to provide a formal definition of untrained anomaly detection problem based on 3D point cloud data, discuss the differences between untrained anomaly detection and current unsupervised anomaly detection methods. Unlike unsupervised learning, untrained methods do not rely on any data, including unlabeled data. Instead, they leverage prior knowledge about the manufacturing surfaces and anomalies. Examples are used to illustrate these prior knowledge and untrained machine learning model. Afterwards, literature review on untrained anomaly detection based on 3D point cloud data is also provided, and the potential of untrained deep neural networks for anomaly detection is also discussed as outlooks.

Related papers

Towards Zero-shot 3D Anomaly Localization [58.62650061201283]
3DzAL is a novel patch-level contrastive learning framework for 3D anomaly detection and localization. We show that 3DzAL outperforms the state-of-the-art anomaly detection and localization performance.
arXiv Detail & Related papers (2024-12-05T16:25:27Z)
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 Con$$, which learns through context augmentations.
arXiv Detail & Related papers (2024-05-29T07:59:06Z)
Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
arXiv Detail & Related papers (2024-01-06T07:30:41Z)
Precursor-of-Anomaly Detection for Irregular Time Series [31.73234935455713]
We present a novel type of anomaly detection, called Precursor-of-Anomaly (PoA) detection. To solve both problems at the same time, we present a neural controlled differential equation-based neural network and its multi-task learning algorithm.
arXiv Detail & Related papers (2023-06-27T14:10:09Z)
The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization [17.437967037670813]
We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It is inspired by real-world visual inspection scenarios in which a model has to detect various types of defects on manufactured products.
arXiv Detail & Related papers (2021-12-16T17:35:51Z)
SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
arXiv Detail & Related papers (2021-11-25T03:53:43Z)
Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
We introduce a novel weakly-supervised anomaly detection framework to train detection models. The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability. Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
arXiv Detail & Related papers (2021-08-01T14:33:17Z)
Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators [0.0]
Anomaly detection is a challenging task for machine learning algorithms due to the inherent class imbalance. Inspired by generative models and the analysis of the hidden activations of neural networks, we introduce a novel unsupervised anomaly detection method called DA3D.
arXiv Detail & Related papers (2021-01-12T18:07:34Z)
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning [113.81927544121625]
Anomaly detection in video is a challenging computer vision problem. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level.
arXiv Detail & Related papers (2020-11-15T10:21:28Z)
Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks [2.7173993697663086]
Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Deep learning Convolutional Neural Networks (CNNs) have been at the forefront of these image processing-based solutions. In this paper, we address that challenge by training the CNN on surface texture patches with a distance-based anomaly detection objective.
arXiv Detail & Related papers (2020-11-09T00:35:21Z)

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