Puzzle-AE: Novelty Detection in Images through Solving Puzzles

08/29/2020
by   Mohammadreza Salehi, et al.
17

Autoencoder (AE) has proved to be an effective framework for novelty detection. However, they do not typically show promising results on other kinds of real-world datasets, which are exhibiting high intra-class variations, such as CIFAR-10. AEs are not generally able to learn a latent space that solely captures common features of the normal class, resulting in both high false positive and false negative rates due to modeling features that are irrelevant to the normal class. Recently, self-supervised learning has shown great promise in representation learning. To this end, we propose a new AE framework that is trained based on solving puzzles on randomly permuted image patches. Based on this framework, we achieve competitive or superior results compared to SOTA anomaly detection methods on various toy and real-world datasets. Unlike many competitors in this field, the proposed framework is stable, has real-time performance, more general and agnostic to choices of the model hyper-parameters, can work effectively under small sample size settings, and does not require unprincipled early stopping.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 8

research
04/08/2021

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

We aim at constructing a high performance model for defect detection tha...
research
08/18/2023

CARLA: A Self-supervised Contrastive Representation Learning Approach for Time Series Anomaly Detection

We introduce a Self-supervised Contrastive Representation Learning Appro...
research
07/31/2021

Margin-Aware Intra-Class Novelty Identification for Medical Images

Traditional anomaly detection methods focus on detecting inter-class var...
research
10/06/2021

A Fast Randomized Algorithm for Massive Text Normalization

Many popular machine learning techniques in natural language processing ...
research
09/10/2021

Enhancing Unsupervised Anomaly Detection with Score-Guided Network

Anomaly detection plays a crucial role in various real-world application...
research
07/05/2023

Information-Based Heavy Hitters for Real-Time DNS Data Exfiltration Detection and Prevention

Data exfiltration over the DNS protocol and its detection have been rese...
research
01/27/2021

Periodic seismicity detection without declustering

Any periodic variations of earthquake occurrence rates in response to sm...

Please sign up or login with your details

Forgot password? Click here to reset