# Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders

arXiv: https://arxiv.org/abs/2012.11113 · HTML: https://mlsanity.com/paper/2012.11113/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learning](https://mlsanity.com/paper/2403.15463/) (2024)
- [Memory Efficient Continual Learning for Edge-Based Visual Anomaly Detection](https://mlsanity.com/paper/2503.02691/) (2025)
- [A deep learning approach for detection and localization of leaf anomalies](https://mlsanity.com/paper/2210.03558/) (2022)
- [PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings](https://mlsanity.com/paper/2505.17614/) (2025)

## Abstract (arXiv)

Autoencoder and its variants have been widely applicated in anomaly detection.The previous work memory-augmented deep autoencoder proposed memorizing normality to detect anomaly, however it neglects the feature discrepancy between different resolution scales, therefore we introduce multi-scale memories to record scale-specific features and multi-scale attention fuser between the encoding and decoding module of the autoencoder for anomaly detection, namely MMAE.MMAE updates slots at corresponding resolution scale as prototype features during unsupervised learning. For anomaly detection, we accomplish anomaly removal by replacing the original encoded image features at each scale with most relevant prototype features,and fuse these features before feeding to the decoding module to reconstruct image. Experimental results on various datasets testify that our MMAE successfully removes anomalies at different scales and performs favorably on several datasets compared to similar reconstruction-based methods.