CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

Published in

Computer Vision and Pattern Recognition(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

This work proposes a two-stage framework for building anomaly detectors using normal training data only, which first learns self-supervised deep representations and then builds a generative one-class classifier on learned representations.

Abstract

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. We learn representations by classifying normal data from the CutPaste, a simple data augmentation strategy that cuts an image patch and pastes at a random location of a large image. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects. We bring the improvement upon previous arts by 3.1 AUCs when learning representations from scratch. By transfer learning on pretrained representations on ImageNet, we achieve a new state-of-the-art 96.6 AUC. Lastly, we extend the framework to learn and extract representations from patches to allow localizing defective areas without annotations during training.

Authors

Kihyuk Sohn

8 papers

Tomas Pfister

7 papers

Jinsung Yoon

4 papers

References67 items

ScaleNet: An Unsupervised Representation Learning Method for Limited Information

Learning and Evaluating Representations for Deep One-class Classification

Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks

A Unifying Review of Deep and Shallow Anomaly Detection

Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

Published in

Computer Vision and Pattern Recognition(2021)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Kihyuk Sohn

8 papers

Tomas Pfister

7 papers

Jinsung Yoon

4 papers

References67 items

ScaleNet: An Unsupervised Representation Learning Method for Limited Information

Learning and Evaluating Representations for Deep One-class Classification

Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks

A Unifying Review of Deep and Shallow Anomaly Detection

Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise

Chun-Liang Li

3 papers

Puzzle-AE: Novelty Detection in Images through Solving Puzzles

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Explainable Deep One-Class Classification

Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation

Density of States Estimation for Out-of-Distribution Detection

Why Normalizing Flows Fail to Detect Out-of-Distribution Data

Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

Sub-Image Anomaly Detection with Deep Pyramid Correspondences

Classification-Based Anomaly Detection for General Data

Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics

A Simple Framework for Contrastive Learning of Visual Representations

Self-supervised learning for medical image analysis using image context restoration

Inverse-Transform AutoEncoder for Anomaly Detection

Attention Guided Anomaly Localization in Images

Momentum Contrast for Unsupervised Visual Representation Learning

Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings

Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality

Likelihood Ratios for Out-of-Distribution Detection

MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

Unsupervised Embedding Learning via Invariant and Spreading Instance Feature

WAIC, but Why? Generative Ensembles for Robust Anomaly Detection

Deep Anomaly Detection with Outlier Exposure

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Representation Learning with Contrastive Predictive Coding

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

Deep One-Class Classification

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

Deep Anomaly Detection Using Geometric Transformations

Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

Unsupervised Representation Learning by Predicting Image Rotations

Real-World Anomaly Detection in Surveillance Videos

Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity

mixup: Beyond Empirical Risk Minimization

Random Erasing Data Augmentation

Improved Regularization of Convolutional Neural Networks with Cutout

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Identifying and Categorizing Anomalies in Retinal Imaging Data

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

SGDR: Stochastic Gradient Descent with Warm Restarts

Deep Structured Energy Based Models for Anomaly Detection

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

Deep Residual Learning for Image Recognition

Detecting anomalous structures by convolutional sparse models

Support Vector Data Description

Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

Scikit-learn: Machine Learning in Python

Anomaly detection: A survey

ImageNet: A large-scale hierarchical image database

Introduction to Nonparametric Estimation

Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors

Support Vector Method for Novelty Detection

Classifier Two Sample Test for Video Anomaly Detections

dsprites: Disentanglement testing sprites dataset

Learning Multiple Layers of Features from Tiny Images

Gradient-based learning applied to document recognition

This Paper Is Included in the Proceedings of the 12th Usenix Symposium on Operating Systems Design and Implementation (osdi '16). Tensorflow: a System for Large-scale Machine Learning Tensorflow: a System for Large-scale Machine Learning

Thomas Schlegl, Philipp Seeb ¨ ock, Sebastian M Waldstein, Ursula Schmidt-Erfurth, and Georg Langs

Spotting defects! — deep metric learning solution for mvtec anomaly detection 9

Field of Study

Computer Science

Journal Information

Name

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Page

10708-10717

Venue Information

Name

Computer Vision and Pattern Recognition

Type

conference

URL

https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000147

Alternate Names

CVPR
Comput Vis Pattern Recognit