Multi-Resolution Fusion: An Effective Approach to Anomaly Detection
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
Unsupervised anomaly detection has been profoundly impacted by the advent of large-scale Vision Foundation Models (VFMs). The prevailing paradigm leverages features from a pre-trained encoder, where anomalies manifest as statistical outliers. However, a fundamental challenge persists: industrial defects vary dramatically in scale, making it difficult for a single model to detect them all effectively. This paper introduces a critical insight: a "division of labor" exists between different input resolutions. We find that low-resolution inputs excel at robustly recognizing the presence of anomalies by capturing global context, while high-resolution inputs are essential for refining their segmentation boundaries with precision. To harness this synergy, we propose Multi-Resolution Fusion (MRF), a simple yet powerful training-free strategy. MRF constructs a feature pyramid from the input space by processing an image at multiple resolutions. By fusing features from this pyramid, our method, MRF-AD, effectively combines the recognition capabilities of low-resolution views with the refinement capabilities of high-resolution ones. Extensive experiments show that MRF-AD achieves highly competitive, and in several cases state-of-the-art, results on challenging benchmarks like MVTec AD 2, proving the efficacy of our multi-resolution approach.
BibTeX
@misc{zou2026multi,
author = {Bocheng Zou and Mu Cai and Yong Jae Lee},
title = {{Multi-Resolution Fusion: An Effective Approach to Anomaly Detection}},
year = {2026},
url = {https://openreview.net/forum?id=Mg5S5Twrfn},
howpublished = {OpenReview},
note = {Submitted to ICLR 2026},
}Loading related content...