ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection

26 May 2023  ยท  Jeeho Hyun, Sangyun Kim, Giyoung Jeon, Seung Hwan Kim, Kyunghoon Bae, Byung Jun Kang ยท

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection BTAD ReConPatch Segmentation AUROC 97.5 # 6
Detection AUROC 95.8 # 1
Anomaly Detection MVTec AD ReConPatch WRN-101 Detection AUROC 99.62 # 9
Segmentation AUROC 98.53 # 15
Anomaly Detection MVTec AD ReConPatch WRN-50 (+RefineNet) Segmentation AUROC 98.62 # 13
Anomaly Detection MVTec AD ReConPatch Ensemble Detection AUROC 99.71 # 4
Segmentation AUROC 98.67 # 12
Anomaly Detection MVTec AD ReConPatch Ensemble (+RefineNet) Detection AUROC 99.86 # 1
Segmentation AUROC 99.2 # 1
Anomaly Detection MVTec AD ReConPatch WRN-50 Segmentation AUROC 98.18 # 31

Methods


No methods listed for this paper. Add relevant methods here