paper-with-me

홈 › Papers

Variational Autoencoder for Anomaly Detection: A Comparative Study

2024-08-24 · Huy Hoang Nguyen, Cuong Nhat Nguyen, Xuan Tung Dao, Quoc Trung Duong, Dzung Pham Thi Kim, Minh-Tan Pham

This paper aims to conduct a comparative analysis of contemporary Variational Autoencoder (VAE) architectures employed in anomaly detection, elucidating their performance and behavioral characteristics within this specific task. The architectural configurations under consideration encompass the original VAE baseline, the VAE with a Gaussian Random Field prior (VAE-GRF), and the VAE incorporating a vision transformer (ViT-VAE). The findings reveal that ViT-VAE exhibits exemplary performance across various scenarios, whereas VAE-GRF may necessitate more intricate hyperparameter tuning to attain its optimal performance state. Additionally, to mitigate the propensity for over-reliance on results derived from the widely used MVTec dataset, this paper leverages the recently-public MiAD dataset for benchmarking. This deliberate inclusion seeks to enhance result competitiveness by alleviating the impact of domain-specific models tailored exclusively for MVTec, thereby contributing to a more robust evaluation framework. Codes is available at https://github.com/endtheme123/VAE-compare.git.

📄 PDF Abstract BibTeX arXiv:2408.13561

Code (1)

endtheme123/vae-compare 공식 구현 pytorch

Tasks

Anomaly DetectionBenchmarking

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

An Attention-Augmented VAE-BiLSTM Framework for Anomaly Detection in 12-Lead ECG Signals

2025-10-07 · Marc Garreta Basora, Mehmet Oguz Mulayim arxiv

Anomaly detection in 12-lead electrocardiograms (ECGs) is critical for identifying deviations associated with cardiovascular disease. This work presents a comparative analysis of three autoencoder-based architectures: co…

Unsupervised Anomaly Detection

Variational Autoencoder based Anomaly Detection using Reconstruction Probability

2015-12-27 · Special Lecture on IE, SNU Data Mining Center 2015 12 · Jinwon An, Sungzoon Cho

We propose an anomaly detection method using the reconstruction probability from the variational autoencoder. The reconstruction probability is a probabilistic measure that takes into account the variability of the distr…

Anomaly Detection

Can I trust my anomaly detection system? A case study based on explainable AI

2024-07-29 · Muhammad Rashid, Elvio Amparore, Enrico Ferrari, Damiano Verda

Generative models based on variational autoencoders are a popular technique for detecting anomalies in images in a semi-supervised context. A common approach employs the anomaly score to detect the presence of anomalies,…

Anomaly Detection

Hierarchical Conditional Variational Autoencoder Based Acoustic Anomaly Detection

2022-06-11 · Harsh Purohit, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi

This paper aims to develop an acoustic signal-based unsupervised anomaly detection method for automatic machine monitoring. Existing approaches such as deep autoencoder (DAE), variational autoencoder (VAE), conditional v…

Anomaly DetectionUnsupervised Anomaly Detection

Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study

2026-01-03 · Ata Akbari Asanjan, Milad Memarzadeh, Bryan Matthews, Nikunj Oza arxiv

In this study, we focus on the training process and inference improvements of deep neural networks (DNNs), specifically Autoencoders (AEs) and Variational Autoencoders (VAEs), using Random Fourier Transformation (RFT). W…

Anomaly Detection