Re Learning Memory Guided Normality for Anomaly Detection

01/29/2021
by   Kevin Stephen, et al.
15

The authors have introduced a novel method for unsupervised anomaly detection that utilises a newly introduced Memory Module in their paper. We validate the authors claim that this helps improve performance by helping the network learn prototypical patterns, and uses the learnt memory to reduce the representation capacity of Convolutional Neural Networks. Further, we validate the efficacy of two losses introduced by the authors, Separateness Loss and Compactness Loss presented to increase the discriminative power of the memory items and the deeply learned features. We test the efficacy with the help of t-SNE plots of the memory items.

READ FULL TEXT

page 9

page 11

page 12

page 13

research
03/30/2020

Learning Memory-guided Normality for Anomaly Detection

We address the problem of anomaly detection, that is, detecting anomalou...
research
01/28/2023

Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore

In the area of fewshot anomaly detection (FSAD), efficient visual featur...
research
04/30/2021

Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings

Recent efforts towards video anomaly detection try to learn a deep autoe...
research
09/26/2022

Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimation

Reconstruction method based on the memory module for visual anomaly dete...
research
08/09/2023

Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection

Anomaly detection has gained considerable attention due to its broad ran...
research
01/06/2022

Memory-guided Image De-raining Using Time-Lapse Data

This paper addresses the problem of single image de-raining, that is, th...
research
04/21/2010

Modelling Immunological Memory

Accurate immunological models offer the possibility of performing highth...

Please sign up or login with your details

Forgot password? Click here to reset