ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection

TL;DR

ReConPatch introduces a contrastive patch representation learning method that enhances industrial anomaly detection by training on pre-trained features, achieving state-of-the-art results on key datasets.

Contribution

The paper proposes ReConPatch, a novel contrastive learning approach that constructs discriminative patch features for industrial anomaly detection without requiring input augmentation.

Findings

Achieved 99.72% accuracy on MVTec AD dataset.

Achieved 95.8% accuracy on BTAD dataset.

Outperforms existing methods in industrial anomaly detection.

Abstract

Anomaly detection is crucial to the advanced identification of product defects such as incorrect parts, misaligned components, and damages in industrial manufacturing. Due to the rare observations and unknown types of defects, anomaly detection is considered to be challenging in machine learning. To overcome this difficulty, recent approaches utilize the common visual representations pre-trained from natural image datasets and distill the relevant features. However, existing approaches still have the discrepancy between the pre-trained feature and the target data, or require the input augmentation which should be carefully designed, particularly for the industrial dataset. In this paper, we introduce ReConPatch, which constructs discriminative features for anomaly detection by training a linear modulation of patch features extracted from the pre-trained model. ReConPatch employs contrastive representation learning to collect and distribute features in a way that produces a target-oriented and easily separable representation. To address the absence of labeled pairs for the contrastive learning, we utilize two similarity measures between data representations, pairwise and contextual similarities, as pseudo-labels. Our method achieves the state-of-the-art anomaly detection performance (99.72%) for the widely used and challenging MVTec AD dataset. Additionally, we achieved a state-of-the-art anomaly detection performance (95.8%) for the BTAD dataset.