Conditional Frechet Inception Distance

Soloveitchik, Michael; Diskin, Tzvi; Morin, Efrat; Wiesel, Ami

doi:10.48550/arxiv.2103.11521

Cited by 5 publications

(5 citation statements)

References 26 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5. The Flechet inception distance (FID) 30 is then used for the discrimination. Experiments: we evaluate our proposed anomaly detection technique on a NDT industrial dataset and the MVTec dataset.…”

Section: Discussionmentioning

confidence: 99%

f-AnoGAN for non-destructive testing in industrial anomaly detection

Sliti

Devanne

Kohler

et al. 2023

Sixteenth International Conference on Quality Control by Artificial Vision

View full text Add to dashboard Cite

Being able to identify defects is an essential step during manufacturing processes. Yet, not all defects are necessarily known and sufficiently well described in the databases images. The challenge we address in this paper is to detect any defect by fitting a model using only normal samples of industrial parts. For this purpose, we propose to test fast AnoGAN (f-AnoGAN) approach based on a generative adversarial network (GAN). The method is an unsupervised learning algorithm, that contains two phases; first, we train a generative model using only normal images, which proposes a fast mapping of new data into the latent space. Second, we add and train an encoder to reconstruct images. The anomaly detection is defined by the reconstruction error between the defected data and the reconstructed ones, and the residual error of the discriminator. For our experiments, we use two sets of industrial data; the MVTec Anomaly Detection Dataset and a private dataset which is based on thermal-wave and used for non-destructive testing. This technique has been utilized in research for the evaluation of industrial materials. Applying the f-AnoGAN in this domain offers high anomaly detection accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

f-AnoGAN for non-destructive testing in industrial anomaly detection

Sliti

Devanne

Kohler

et al. 2023

Sixteenth International Conference on Quality Control by Artificial Vision

View full text Add to dashboard Cite

show abstract

“…We report results for several different metrics, including peak-signal-to-noise ratio (PSNR), structural-similarity index (SSIM) (Wang et al, 2004), Fréchet Inception Score (FID) (Heusel et al, 2017), and conditional FID (cFID) (Soloveitchik et al, 2021). PSNR and SSIM were computed on the average of P posterior samples {i p } P p=1 , i.e.,…”

Section: Discussionmentioning

confidence: 99%

Continuous and Distribution-free Probabilistic Wind Power Forecasting: A Conditional Normalizing Flow Approach

Wen¹,

ma²,

Gu³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow~(CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches) and can directly yield continuous probability densities, hence avoiding quantile crossing. It relies on a base distribution and a set of bijective mappings. Both the shape parameters of the base distribution and the bijective mappings are approximated with neural networks. Spline-based conditional normalizing flow is considered owing to its universal approximation capability. Over the training phase, the model sequentially maps input examples onto samples of base distribution, where parameters are estimated through maximum likelihood. To issue probabilistic forecasts, one eventually map samples of the base distribution into samples of a desired distribution. Case studies based on open datasets validate the effectiveness of the proposed model, and allows us to discuss its advantages and caveats with respect to the state of the art. Code will be released upon publication.

show abstract

“…The Fréchet Inception Distance (FID) is a metric used to evaluate the quality of images generated by a generative model. Specifically, this criterion has been developed for assessing the performance of GANs [51]. FID calculates the distance between feature vectors of real and generated (fake) images produced by the generative model.…”

Section: Fréchet Inception Distance (Fid)mentioning

confidence: 99%

“…FID calculates the distance between feature vectors of real and generated (fake) images produced by the generative model. A low FID value indicates that the quality of the generated images by the generative model is higher and more similar to real images [51]. The FID results for different image datasets are recorded in Table 10.…”

Section: Fréchet Inception Distance (Fid)mentioning

confidence: 99%

A new hierarchical algorithm based on CapsGAN for imbalanced image classification

Jabbari,

Bigdeli

2023

IET Image Processing

View full text Add to dashboard Cite

Imbalanced image datasets consist of image datasets where there is a significant disparity in the number of samples across different classes. With imbalanced image datasets, learning algorithms often tend to be biased toward the majority class samples. This leads to poor classification of minority class samples as their training is not properly conducted. It becomes more complicated when the number of samples in the minority class is very low. In this paper, a novel hierarchical algorithm is proposed for generating new data using Capsule Generative Adversarial Networks (CapsGAN) to address the class imbalance problem in imbalanced image datasets. Unlike common GAN models, the proposed method incorporates an auxiliary CapsNet to identify high‐value images in both minority and majority classes. This identification is based on the ability to detect complex relationships between low‐level and high‐level features present in capsule networks. Furthermore, the proposed CapsGAN model is conditioned to generate minority class samples based on feature vectors of last capsule layer to achieve a more balanced image dataset. For evaluating the performance of the proposed model, an image dataset called CICS was collected and introduced. Extensive experiments were also conducted using various online image datasets from different domains, with varying numbers of classes and data sizes. The experimental results demonstrated that the proposed model can generate high‐quality samples in cases where the image dataset or the number of minority class samples is relatively small. Furthermore, the proposed model has maintained an accuracy of over 80% in an imbalanced ratio of 1:60.

show abstract

Conditional Frechet Inception Distance

Cited by 5 publications

References 26 publications

f-AnoGAN for non-destructive testing in industrial anomaly detection

f-AnoGAN for non-destructive testing in industrial anomaly detection

Continuous and Distribution-free Probabilistic Wind Power Forecasting: A Conditional Normalizing Flow Approach

A new hierarchical algorithm based on CapsGAN for imbalanced image classification

Contact Info

Product

Resources

About