# Deep Generative Model using Unregularized Score for Anomaly Detection with Heterogeneous Complexity

arXiv: https://arxiv.org/abs/1807.05800 · HTML: https://mlsanity.com/paper/1807.05800/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2018.

## Built on by (most cited first, 10 of 10)

- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow](https://mlsanity.com/paper/2303.02595/) (2023)
- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [Segment Any Anomaly without Training via Hybrid Prompt Regularization](https://mlsanity.com/paper/2305.10724/) (2023)
- [Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection](https://mlsanity.com/paper/2404.09654/) (2024)
- [Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction](https://mlsanity.com/paper/2304.02216/) (2023)
- [Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework](https://mlsanity.com/paper/2409.13162/) (2024)
- [ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement](https://mlsanity.com/paper/2407.17705/) (2024)
- [Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization](https://mlsanity.com/paper/2605.28428/) (2026)
- [CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection](https://mlsanity.com/paper/2311.06794/) (2023)

## Abstract (arXiv)

Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the probabilistic model assigns undesirably lower likelihoods to complexly shaped objects that are nevertheless consistent with set standards. To overcome this difficulty, we propose an unregularized score for deep generative models (DGMs), which are generative models leveraging deep neural networks. We found that the regularization terms of the DGMs considerably influence the anomaly score depending on the complexity of the samples. By removing these terms, we obtain an unregularized score, which we evaluated on a toy dataset and real-world manufacturing datasets. Empirical results demonstrate that the unregularized score is robust to the inherent complexity of samples and can be used to better detect anomalies.