[DL輪読会]Deep Anomaly Detection Using Geometric Transformations

Mar 29, 20194 likes2,370 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

: 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
!"($) !&($) !'($) !(($)
( )
( )

:
n (PCA, Robust-PCA, deep autoencoders, ADGAN…)
n
n One Class SVM
L2

:
n
n (KDE, Robust-KDE, DSEBM…)
n One Class SVM

:
n
n
n One Class SVM (SVDD, Deep SVDD...)

: step1
n k
n identity transformation
n
n x
cross-entropy
deep k-class
!"
72(=2x3x3x4)

: step2 Dirichlet Normality Score
n softmax y(x) (Dirichlet ) α
n α
x

:
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

:
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

: AUROC
n AUROC(area under an ROC curve)
http://www.randpy.tokyo/entry/roc_auc
AUROC

This document summarizes recent advances in single image super-resolution (SISR) using deep learning methods. It discusses early SISR networks like SRCNN, VDSR and ESPCN. SRResNet is presented as a baseline method, incorporating residual blocks and pixel shuffle upsampling. SRGAN and EDSR are also introduced, with EDSR achieving state-of-the-art PSNR results. The relationship between reconstruction loss, perceptual quality and distortion is examined. While PSNR improves yearly, a perception-distortion tradeoff remains. Developments are ongoing to produce outputs that are both accurately restored and naturally perceived.

論文紹介：Grad-CAM: Visual explanations from deep networks via gradient-based loca...Kazuki Adachi

[Dl輪読会]introduction of reinforcement learningDeep Learning JP

[DL輪読会]相互情報量最大化による表現学習Deep Learning JP

Bayesian Neural Networks : Surveytmtm otm

Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Yusuke Uchida

Skip Connection まとめ（Neural Network）Yamato OKAMOTO

R-CNNの原理とここ数年の流れKazuki Motohashi

動画認識における代表的なモデル・データセット（メタサーベイ）cvpaper. challenge

[DL輪読会]Learning Transferable Visual Models From Natural Language SupervisionDeep Learning JP

Layer Normalization@NIPS+読み会・関西Keigo Nishida

[DL輪読会]World ModelsDeep Learning JP

[DL輪読会]Model soups: averaging weights of multiple fine-tuned models improves ...Deep Learning JP

Contrastive learning 20200607ぱんいちすみもと

深層学習の不確実性 - Uncertainty in Deep Neural Networks -tmtm otm

[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...Deep Learning JP

[DL輪読会]Learning Latent Dynamics for Planning from PixelsDeep Learning JP

畳み込みニューラルネットワークの高精度化と高速化Yusuke Uchida

2012年の画像認識コンペティションILSVRCにおけるAlexNetの登場以降，画像認識においては畳み込みニューラルネットワーク (CNN) を用いることがデファクトスタンダードとなった．CNNは画像分類だけではなく，セグメンテーションや物体検出など様々なタスクを解くためのベースネットワークとしても広く利用されてきている．本講演では，AlexNet以降の代表的なCNNの変遷を振り返るとともに，近年提案されている様々なCNNの改良手法についてサーベイを行い，それらを幾つかのアプローチに分類し，解説する．更に，実用上重要な高速化手法について、畳み込みの分解や枝刈り等の分類を行い，それぞれ解説を行う． Recent Advances in Convolutional Neural Networks and Accelerating DNNs 第21回ステアラボ人工知能セミナー講演資料 https://stair.connpass.com/event/126556/

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving PlannersDeep Learning JP

【DL輪読会】事前学習用データセットについてDeep Learning JP

More Related Content

What's hot (20)

[DL輪読会]Vision Transformer with Deformable Attention （Deformable Attention Tra...Deep Learning JP

【メタサーベイ】数式ドリブン教師あり学習cvpaper. challenge

Deep Learningによる超解像の進歩Hiroto Honda

論文紹介：Grad-CAM: Visual explanations from deep networks via gradient-based loca...Kazuki Adachi

[Dl輪読会]introduction of reinforcement learningDeep Learning JP

[DL輪読会]相互情報量最大化による表現学習Deep Learning JP

Bayesian Neural Networks : Surveytmtm otm

Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Yusuke Uchida

Skip Connection まとめ（Neural Network）Yamato OKAMOTO

R-CNNの原理とここ数年の流れKazuki Motohashi

動画認識における代表的なモデル・データセット（メタサーベイ）cvpaper. challenge

[DL輪読会]Learning Transferable Visual Models From Natural Language SupervisionDeep Learning JP

Layer Normalization@NIPS+読み会・関西Keigo Nishida

[DL輪読会]World ModelsDeep Learning JP

[DL輪読会]Model soups: averaging weights of multiple fine-tuned models improves ...Deep Learning JP

Contrastive learning 20200607ぱんいちすみもと

深層学習の不確実性 - Uncertainty in Deep Neural Networks -tmtm otm

[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...Deep Learning JP

[DL輪読会]Learning Latent Dynamics for Planning from PixelsDeep Learning JP

畳み込みニューラルネットワークの高精度化と高速化Yusuke Uchida

[DL輪読会]Vision Transformer with Deformable Attention （Deformable Attention Tra...Deep Learning JP

【メタサーベイ】数式ドリブン教師あり学習cvpaper. challenge

Deep Learningによる超解像の進歩Hiroto Honda

論文紹介：Grad-CAM: Visual explanations from deep networks via gradient-based loca...Kazuki Adachi

[Dl輪読会]introduction of reinforcement learningDeep Learning JP

[DL輪読会]相互情報量最大化による表現学習Deep Learning JP

Bayesian Neural Networks : Surveytmtm otm

Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Yusuke Uchida

Skip Connection まとめ（Neural Network）Yamato OKAMOTO

R-CNNの原理とここ数年の流れKazuki Motohashi

動画認識における代表的なモデル・データセット（メタサーベイ）cvpaper. challenge

[DL輪読会]Learning Transferable Visual Models From Natural Language SupervisionDeep Learning JP

Layer Normalization@NIPS+読み会・関西Keigo Nishida

[DL輪読会]World ModelsDeep Learning JP

[DL輪読会]Model soups: averaging weights of multiple fine-tuned models improves ...Deep Learning JP

Contrastive learning 20200607ぱんいちすみもと

深層学習の不確実性 - Uncertainty in Deep Neural Networks -tmtm otm

[DL輪読会] Spectral Norm Regularization for Improving the Generalizability of De...Deep Learning JP

[DL輪読会]Learning Latent Dynamics for Planning from PixelsDeep Learning JP

畳み込みニューラルネットワークの高精度化と高速化Yusuke Uchida

More from Deep Learning JP (20)

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving PlannersDeep Learning JP

【DL輪読会】事前学習用データセットについてDeep Learning JP

【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...Deep Learning JP

【DL輪読会】Zero-Shot Dual-Lens Super-ResolutionDeep Learning JP

【DL輪読会】BloombergGPT: A Large Language Model for Finance arxivDeep Learning JP

【DL輪読会】マルチモーダル LLMDeep Learning JP

【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...Deep Learning JP

【DL輪読会】AnyLoc: Towards Universal Visual Place RecognitionDeep Learning JP

【DL輪読会】Can Neural Network Memorization Be Localized?Deep Learning JP

【DL輪読会】Hopfield network　関連研究についてDeep Learning JP

【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )Deep Learning JP

【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...Deep Learning JP

【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"Deep Learning JP

【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "Deep Learning JP

【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat ModelsDeep Learning JP

【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"Deep Learning JP

【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...Deep Learning JP

【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...Deep Learning JP

【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...Deep Learning JP

【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...Deep Learning JP