q-Space Novelty Detection with Variational Autoencoders

Васильев, А. Э.; Golkov, Vladimir; Meissner, Marc; Lipp, Ilona; Sgarlata, Eleonora; Tomassini, Valentina; Jones, Derek K.; Cremers, Daniel

doi:10.1007/978-3-030-52893-5_10

Cited by 30 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described above, the abnormal score function is mostly based on reconstruction loss. In more detail, it varies according to each method, such as a method using L1-distance of the output image and input image [16], [19], method of using the distance of probability distribution in latent space [15], a method using SSIM [18]. The threshold value is defined based on the normal sample's abnormal score value in the training stage.…”

Section: B Inspection Stagementioning

confidence: 99%

“…This method classifies an abnormal sample using the difference in a loss function or mutual information between normal sample and abnormal sample. The autoencoder-based method is an unsupervised-based method composed of an encoder and a decoder [15] - [22]. The autoencoder-based anomaly detection method uses the image difference between input and output images [16], [18], [20], a latent space-based score [15], [17], a loss-based score [19], and the method using the autoencoder-based GAN structure [20].…”

Section: Introductionmentioning

confidence: 99%

“…The autoencoder-based method is an unsupervised-based method composed of an encoder and a decoder [15] - [22]. The autoencoder-based anomaly detection method uses the image difference between input and output images [16], [18], [20], a latent space-based score [15], [17], a loss-based score [19], and the method using the autoencoder-based GAN structure [20]. The autoencoderbased anomaly detection method has higher learning stability than the GAN-based method, making it possible to classify abnormal samples simply by reconstructing the input image and the output image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Anomaly Detection Using Autoencoder With Feature Vector Frequency Map

Kim

Park

2021

IEEE Access

View full text Add to dashboard Cite

Anomaly detection uses various machine learning techniques to identify and classify defective data on the production line. The autoencoder-based anomaly detection method is an unsupervised method that classifies abnormal samples using an autoencoder trained only from normal samples and is useful in environments where it is difficult to obtain abnormal samples. This method uses an abnormal score based on the reconstruction loss function, making it difficult to detect defects, such as stains, having a similar texture to a normal sample. To solve this problem, we propose an anomaly detection method using a vector quantized variational autoencoder and a feature vector frequency map. We use the prototype vector histogram and its frequency for anomaly detection instead of the reconstruction loss function. The prototype vector histogram is obtained from the vector quantized variational autoencoder's codebook in the training stage. The feature vector frequency map of the input image is generated using the prototype vector histogram in the inference stage. We calculated the abnormal score using the generated frequency map and classified the abnormal samples. The experimental results showed that the proposed method has a higher Area Under Receiver Operating Characteristics (AUROC) than the previous method in stain and scratch defects.

show abstract

Section: B Inspection Stagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly Detection Using Autoencoder With Feature Vector Frequency Map

Kim

Park

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Autoencoders are a particular family of NN, principally used for denoising and feature extraction [12]. An autoencoder NN is composed of two parts, an encoder, and a decoder.…”

Section: Introductionmentioning

confidence: 99%

“…This enables the autoencoder NN to codify each input in a small number of features which can then be used for classification or other tasks. Autoencoders have been recently used in dMRI by Vasilev and colleagues to detect abnormal voxels in multiple-sclerosis patients' data [12]. One of the main limitations of using autoencoders with dMRI data is that the dMRI signal is strongly directional-dependent and even a slight change in the orientation in the underlying brain fiber bundles will result in a completely different signal profile.…”

Section: Introductionmentioning

confidence: 99%

Brain Tissue Microstructure Characterization Using dMRI Based Autoencoder Neural-Networks

Zucchelli

Deslauriers-Gauthier

Deriche

2021

Computational Diffusion MRI

View full text Add to dashboard Cite

In recent years, multi-compartmental models have been widely used to try to characterize brain tissue microstructure from Diffusion Magnetic Resonance Imaging (dMRI) data. One of the main drawbacks of this approach is that the number of microstructural features needs to be decided a priori and it is embedded in the model definition. However, the number of microstructural features which is possible to obtain from dMRI data given the acquisition scheme is still not clear. In this work, we aim at characterizing brain tissue using autoencoder neural networks in combination with rotation-invariant features. By changing the number of neurons in the autoencoder latent-space, we can effectively control the number of microstructural features that we obtained from the data. By plotting the autoencoder reconstruction error to the number of features we were able to find the optimal trade-off between data fidelity and the number of microstructural features. Our results show how this number is impacted by the number of shells and the bvalues used to sample the dMRI signal. We also show how our technique paves the way to a richer characterization of the brain tissue microstructure in-vivo.

show abstract

Self‐supervised learning for outlier detection

Diers

Pigorsch

2021

Stat

View full text Add to dashboard Cite

The identification of outliers is mainly based on unannotated data and therefore constitutes an unsupervised problem. The lack of a label leads to numerous challenges that do not occur or only occur to a lesser extent when using annotated data and supervised methods. In this paper, we focus on two of these challenges: the selection of hyperparameters and the selection of informative features. To this end, we propose a method to transform the unsupervised problem of outlier detection into a supervised problem. Benchmarking our approach against common outlier detection methods shows clear advantages of our method when many irrelevant features are present. Furthermore, the proposed approach also scores very well in the selection of hyperparameters, i.e., compared to methods with randomly selected hyperparameters.

show abstract

q-Space Novelty Detection with Variational Autoencoders

Cited by 30 publications

References 7 publications

Anomaly Detection Using Autoencoder With Feature Vector Frequency Map

Anomaly Detection Using Autoencoder With Feature Vector Frequency Map

Brain Tissue Microstructure Characterization Using dMRI Based Autoencoder Neural-Networks

Self‐supervised learning for outlier detection

Contact Info

Product

Resources

About