Multiresolution Knowledge Distillation for Anomaly Detection

by   Mohammadreza Salehi, et al.

Unsupervised representation learning has proved to be a critical component of anomaly detection/localization in images. The challenges to learn such a representation are two-fold. Firstly, the sample size is not often large enough to learn a rich generalizable representation through conventional techniques. Secondly, while only normal samples are available at training, the learned features should be discriminative of normal and anomalous samples. Here, we propose to use the "distillation" of features at various layers of an expert network, pre-trained on ImageNet, into a simpler cloner network to tackle both issues. We detect and localize anomalies using the discrepancy between the expert and cloner networks' intermediate activation values given the input data. We show that considering multiple intermediate hints in distillation leads to better exploiting the expert's knowledge and more distinctive discrepancy compared to solely utilizing the last layer activation values. Notably, previous methods either fail in precise anomaly localization or need expensive region-based training. In contrast, with no need for any special or intensive training procedure, we incorporate interpretability algorithms in our novel framework for the localization of anomalous regions. Despite the striking contrast between some test datasets and ImageNet, we achieve competitive or significantly superior results compared to the SOTA methods on MNIST, F-MNIST, CIFAR-10, MVTecAD, Retinal-OCT, and two Medical datasets on both anomaly detection and localization.



There are no comments yet.


page 1

page 3

page 5

page 6

page 7


Attention Guided Anomaly Detection and Localization in Images

Anomaly detection and localization is a popular computer vision problem ...

A^3: Activation Anomaly Analysis

Inspired by the recent advances in coverage-guided analysis of neural ne...

Attention Guided Anomaly Localization in Images

Anomaly localization is an important problem in computer vision which in...

AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces

Humans can easily detect a defect (anomaly) because it is different or s...

The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization

We introduce the first comprehensive 3D dataset for the task of unsuperv...

Anomaly Detection in Image Datasets Using Convolutional Neural Networks, Center Loss, and Mahalanobis Distance

User activities generate a significant number of poor-quality or irrelev...

Puzzle-AE: Novelty Detection in Images through Solving Puzzles

Autoencoder (AE) has proved to be an effective framework for novelty det...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.