Variational Autoencoder for Anomaly Detection: A Comparative Study
- URL: http://arxiv.org/abs/2408.13561v1
- Date: Sat, 24 Aug 2024 12:07:57 GMT
- Title: Variational Autoencoder for Anomaly Detection: A Comparative Study
- Authors: Huy Hoang Nguyen, Cuong Nhat Nguyen, Xuan Tung Dao, Quoc Trung Duong, Dzung Pham Thi Kim, Minh-Tan Pham,
- Abstract summary: This paper aims to conduct a comparative analysis of contemporary Variational Autoencoder (VAE) architectures employed in anomaly detection.
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)
- Score: 1.9131868049527914
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm [9.132370119093597]
This study introduces Adversarial Variational Bayes (AVB) algorithms as an improvement to VAEs for item factor analysis.
AVB incorporates an auxiliary discriminator network to reframe the estimation process as a two-player adversarial game.
A further enhanced algorithm, Importance-weighted Adversarial Variational Bayes (IWAVB) is proposed and compared with Importance-weighted Autoencoders (IWAE)
arXiv Detail & Related papers (2025-02-15T03:03:09Z) - ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders [0.5759862457142761]
We propose a statistical formulation to discover the relevant latent factors required for modeling a dataset.
We call the proposed method the automatic relevancy detection in the variational autoencoder (ARD-VAE)
arXiv Detail & Related papers (2025-01-18T23:27:05Z) - Analyzing Local Representations of Self-supervised Vision Transformers [34.56680159632432]
We present a comparative analysis of various self-supervised Vision Transformers (ViTs)
Inspired by large language models, we examine the abilities of ViTs to perform various computer vision tasks with little to no fine-tuning.
arXiv Detail & Related papers (2023-12-31T11:38:50Z) - Matching aggregate posteriors in the variational autoencoder [0.5759862457142761]
The variational autoencoder (VAE) is a well-studied, deep, latent-variable model (DLVM)
This paper addresses shortcomings in VAEs by reformulating the objective function associated with VAEs in order to match the aggregate/marginal posterior distribution to the prior.
The proposed method is named the emphaggregate variational autoencoder (AVAE) and is built on the theoretical framework of the VAE.
arXiv Detail & Related papers (2023-11-13T19:22:37Z) - Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models.
In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
arXiv Detail & Related papers (2023-04-04T17:54:32Z) - Vision Transformers are Robust Learners [65.91359312429147]
We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples.
We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
arXiv Detail & Related papers (2021-05-17T02:39:22Z) - Adversarial Feature Augmentation and Normalization for Visual
Recognition [109.6834687220478]
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings.
We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
arXiv Detail & Related papers (2021-03-22T20:36:34Z) - Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
Variational autoencoders (VAE) are a powerful and widely-used class of generative models.
We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs.
Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
arXiv Detail & Related papers (2021-01-06T17:36:26Z) - Autoencoding Variational Autoencoder [56.05008520271406]
We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency.
We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
arXiv Detail & Related papers (2020-12-07T14:16:14Z) - Self-Supervised Variational Auto-Encoders [10.482805367361818]
We present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE)
This class of models allows to perform both conditional and unconditional sampling, while simplifying the objective function.
We present performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA)
arXiv Detail & Related papers (2020-10-05T13:42:28Z) - Recent Developments Combining Ensemble Smoother and Deep Generative
Networks for Facies History Matching [58.720142291102135]
This research project focuses on the use of autoencoders networks to construct a continuous parameterization for facies models.
We benchmark seven different formulations, including VAE, generative adversarial network (GAN), Wasserstein GAN, variational auto-encoding GAN, principal component analysis (PCA) with cycle GAN, PCA with transfer style network and VAE with style loss.
arXiv Detail & Related papers (2020-05-08T21:32:42Z)
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.