Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization

Abstract

The essence of unsupervised anomaly detection is to learn the compact distribution of normal samples and detect outliers as anomalies in testing. Meanwhile, the anomalies in real-world are usually subtle and fine-grained in a high-resolution image especially for industrial applications. Towards this end, we propose a novel framework for unsupervised anomaly detection and localization. Our method aims at learning dense and compact distribution from normal images with a coarse-to-fine alignment process. The coarse alignment stage standardizes the pixel-wise position of objects in both image and feature levels. The fine alignment stage then densely maximizes the similarity of features among all corresponding locations in a batch. To facilitate the learning with only normal images, we propose a new pretext task called non-contrastive learning for the fine alignment stage. Non-contrastive learning extracts robust and discriminating normal image representations without making assumptions on abnormal samples, and it thus empowers our model to generalize to various anomalous scenarios. Extensive experiments on two typical industrial datasets of MVTec AD and BenTech AD demonstrate that our framework is effective in detecting various real-world defects and achieves a new state-of-the-art in industrial unsupervised anomaly detection.

ICME2022 oral

References in corpus (11)

• Improved Regularization of Convolutional Neural Networks with Cutout
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Exploring Simple Siamese Representation Learning
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• Deep Nearest Neighbor Anomaly Detection
• Explainable Deep One-Class Classification
• Classification-Based Anomaly Detection for General Data
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
• Identifying and Categorizing Anomalies in Retinal Imaging Data
• VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization