# Divide and Conquer: High-Resolution Industrial Anomaly Detection via Memory Efficient Tiled Ensemble

arXiv: https://arxiv.org/abs/2403.04932 · HTML: https://mlsanity.com/paper/2403.04932/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 46 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 5 of 5)

- [Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders](https://mlsanity.com/paper/1807.02011/) (2018)
- [FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows](https://mlsanity.com/paper/2111.07677/) (2021)
- [Student-Teacher Feature Pyramid Matching for Anomaly Detection](https://mlsanity.com/paper/2103.04257/) (2021)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection](https://mlsanity.com/paper/2311.09999/) (2023)

## Abstract (arXiv)

Industrial anomaly detection is an important task within computer vision with a wide range of practical use cases. The small size of anomalous regions in many real-world datasets necessitates processing the images at a high resolution. This frequently poses significant challenges concerning memory consumption during the model training and inference stages, leaving some existing methods impractical for widespread adoption. To overcome this challenge, we present the tiled ensemble approach, which reduces memory consumption by dividing the input images into a grid of tiles and training a dedicated model for each tile location. The tiled ensemble is compatible with any existing anomaly detection model without the need for any modification of the underlying architecture. By introducing overlapping tiles, we utilize the benefits of traditional stacking ensembles, leading to further improvements in anomaly detection capabilities beyond high resolution alone. We perform a comprehensive analysis using diverse underlying architectures, including Padim, PatchCore, FastFlow, and Reverse Distillation, on two standard anomaly detection datasets: MVTec and VisA. Our method demonstrates a notable improvement across setups while remaining within GPU memory constraints, consuming only as much GPU memory as a single model needs to process a single tile.