# Memory-Distilled Selection for Noise-Robust Anomaly Detection

arXiv: https://arxiv.org/abs/2605.26676 · HTML: https://mlsanity.com/paper/2605.26676/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 16 of 16)

- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection](https://mlsanity.com/paper/2403.12580/) (2024)
- [Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2405.14325/) (2024)
- [Deep One-Class Classification via Interpolated Gaussian Descriptor](https://mlsanity.com/paper/2101.10043/) (2021)
- [Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2310.14228/) (2023)
- [SoftPatch: Unsupervised Anomaly Detection with Noisy Data](https://mlsanity.com/paper/2403.14233/) (2024)
- [Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection](https://mlsanity.com/paper/2503.02424/) (2025)
- [Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.06115/) (2021)
- [TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection](https://mlsanity.com/paper/2504.02775/) (2025)

## Built on by (most cited first, 1 of 1)

- [What Memory Composition Does Not Tell Us About Anomaly Detection](https://mlsanity.com/paper/2608.23295/) (2026)

## Abstract (arXiv)

Anomaly detection (AD) under data contamination is critical for deploying unsupervised defect detection in industrial environments, where curating perfectly clean training sets is impractical. However, existing methods are sensitive to contamination, suffering significant performance degradation as the noise ratio increases. In this paper, we propose Memory-Distilled Selection (MeDS), a training algorithm based on data selection. MeDS constructs an ensemble of partial memories via random subsampling, where the resulting sparsity acts as a low-pass filter that captures nominal patterns across a wide range of noise ratios, enabling coarse-level identification of contaminated samples. The aggregated distances to the bootstrapped memories are then distilled into a reconstruction score network, which is subsequently fine-tuned on clean data filtered using scores from the distilled model, enabling fine-grained localization of anomalies. MeDS is robust across a wide range of noise ratios without requiring noise-ratio-specific hyperparameter tuning, achieving 99.16% image-level AUROC on MVTecAD at a 40% noise ratio, and attaining state-of-the-art performance on both VisA and Real-IAD under noisy settings. We thoroughly verify the efficacy of MeDS on industrial AD benchmarks under noisy data scenarios, accompanied by in-depth empirical analyses.