# Exploring Deep Anomaly Detection Methods Based on Capsule Net

arXiv: https://arxiv.org/abs/1907.06312 · HTML: https://mlsanity.com/paper/1907.06312/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Deep One-Class Classification via Interpolated Gaussian Descriptor](https://mlsanity.com/paper/2101.10043/) (2021)
- [Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimation](https://mlsanity.com/paper/2209.12441/) (2022)
- [Unsupervised Two-Stage Anomaly Detection](https://mlsanity.com/paper/2103.11671/) (2021)
- [Unsupervised Visual Defect Detection with Score-Based Generative Model](https://mlsanity.com/paper/2211.16092/) (2022)
- [Data Invariants to Understand Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/2111.13362/) (2021)
- [Anomaly Detection with Adversarially Learned Perturbations of Latent Space](https://mlsanity.com/paper/2207.01106/) (2022)
- [Augment to Detect Anomalies with Continuous Labelling](https://mlsanity.com/paper/2207.01112/) (2022)

## Abstract (arXiv)

In this paper, we develop and explore deep anomaly detection techniques based on the capsule network (CapsNet) for image data. Being able to encoding intrinsic spatial relationship between parts and a whole, CapsNet has been applied as both a classifier and deep autoencoder. This inspires us to design a prediction-probability-based and a reconstruction-error-based normality score functions for evaluating the "outlierness" of unseen images. Our results on three datasets demonstrate that the prediction-probability-based method performs consistently well, while the reconstruction-error-based approach is relatively sensitive to the similarity between labeled and unlabeled images. Furthermore, both of the CapsNet-based methods outperform the principled benchmark methods in many cases.