A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

04/29/2021
by   Shelly Sheynin, et al.
16

Anomaly detection, the task of identifying unusual samples in data, often relies on a large set of training samples. In this work, we consider the setting of few-shot anomaly detection in images, where only a few images are given at training. We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. We further enhance the representation of our model by using image transformations and optimize scale-specific patch-discriminators to distinguish between real and fake patches of the image, as well as between different transformations applied to those patches. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions. We demonstrate the superiority of our method on both the one-shot and few-shot settings, on the datasets of Paris, CIFAR10, MNIST and FashionMNIST as well as in the setting of defect detection on MVTec. In all cases, our method outperforms the recent baseline methods.

READ FULL TEXT

page 2

page 6

page 7

page 8

research
02/11/2022

From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach

Anomaly detection from graph data is an important data mining task in ma...
research
05/15/2020

Transformation Based Deep Anomaly Detection in Astronomical Images

In this work, we propose several enhancements to a geometric transformat...
research
10/03/2022

One-shot Detail Retouching with Patch Space Neural Field based Transformation Blending

Photo retouching is a difficult task for novice users as it requires exp...
research
04/28/2021

Inpainting Transformer for Anomaly Detection

Anomaly detection in computer vision is the task of identifying images w...
research
02/24/2021

Railway Anomaly detection model using synthetic defect images generated by CycleGAN

Although training data is essential for machine learning, railway compan...
research
01/19/2023

Hybrid Open-set Segmentation with Synthetic Negative Data

Open-set segmentation is often conceived by complementing closed-set cla...
research
07/16/2018

Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score

One of the most common needs in manufacturing plants is rejecting produc...

Please sign up or login with your details

Forgot password? Click here to reset