[DL輪読会]Deep Anomaly Detection Using Geometric Transformations
4 likes2,376 views
This document summarizes several deep learning papers on anomaly detection. It discusses techniques like one class SVM, autoencoders, and generative adversarial networks. It also reviews benchmark datasets commonly used to evaluate anomaly detection methods like CIFAR-10, CIFAR-100, Fashion-MNIST, and CatsVsDogs. Area under the ROC curve (AUROC) is identified as a common metric for comparing the performance of different anomaly detection methods on these datasets.
![1
DEEP LEARNING JP
[DL Papers]
http://deeplearning.jp/
Hirono Okamoto, Matsuo Lab](https://image.slidesharecdn.com/deepanomalydetectionusinggeometrictransformations-190329122109/85/DL-Deep-Anomaly-Detection-Using-Geometric-Transformations-1-320.jpg)
[DL輪読会]Deep Anomaly Detection Using Geometric Transformations
- 1. 1 DEEP LEARNING JP [DL Papers] http://deeplearning.jp/ Hirono Okamoto, Matsuo Lab
- 2. : Deep Anomaly Detection Using Geometric Transformations n NIPS 2018 accepted n : Izhak Golan, Ran El-Yaniv n : n ( flip ) n n AUROC OC-SVM, DAGMM, DSEBM, ADGAN SOTA !"($) !&($) !'($) !(($) ( ) ( )
- 3. : n 1: n 2: 1 (2 ) ( ) ( )
- 4. : n n n One Class SVM
- 5. : n (PCA, Robust-PCA, deep autoencoders, ADGAN…) n n One Class SVM L2
- 6. : n n (KDE, Robust-KDE, DSEBM…) n One Class SVM
- 7. : n n n One Class SVM (SVDD, Deep SVDD...)
- 9. : step1 n k n identity transformation n n x cross-entropy deep k-class !" 72(=2x3x3x4)
- 10. : step2 Dirichlet Normality Score n softmax y(x) (Dirichlet ) α n α x
- 12. : n k f n α y n !"($) !"($)
- 13. : n One-Class SVM (OC-SVM) n RAW-OC-SVM n CAE-OC-SVM n Deep One-Class Classification (E2E-OC-SVM) n ICML2018 n Deep structured energy-based models (DSEBM) n ICML 2016 n n Deep Autoencoding Gaussian Mixture Model (DAGMM) n ICLR 2018 n n Anomaly Detection with a Generative Adversarial Network (ADGAN) n AnoGAN(IPMI 2017) n GAN
- 14. : n CIFAR-10 n 10 6000 32x32 n CIFAR-100 n 100 600 32x32 n 20 n Fashion-MNIST n 10 7000 28x28 n CatsVsDogs n ASIRRA n 2 12500 360x400 64x64
- 15. : AUROC n AUROC(area under an ROC curve) http://www.randpy.tokyo/entry/roc_auc AUROC
- 16. : CIFAR-10 SOTA
- 17. : CIFAR-100 SOTA
- 19. n n n GAN SOTA n n ( ?) n