Skip to main content
Self-supervised predictive convolutional attentive block for anomaly detection
  • Nicolae-Catalin Ristea, University Politehnica of Bucharest & Mohamed bin Zayed University of Artificial Intelligence
  • Neelu Madan, Aalborg University
  • Radu Tudor Ionescu, University of Bucharest & SecurifAI
  • Kamal Nasrollahi, Aalborg University & Milestone Systems
  • Fahad Shahbaz Khan, Mohamed Bin Zayed University of Artificial Intelligence & Aalborg University
  • Thomas B. Moeslund, Aalborg University
  • Mubarak Shah, University of Central Florida
Document Type

Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. The proposed self-supervised block is generic and can easily be incorporated into various state-of-the-art anomaly detection methods. Our block starts with a convolutional layer with dilated filters, where the center area of the receptive field is masked. The resulting activation maps are passed through a channel attention module. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video, providing empirical evidence that shows considerable performance improvements on MVTec AD, Avenue, and ShanghaiTech. Copyright © 2021, The Authors. All rights reserved.

Publication Date
  • Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Preprint: arXiv

Citation Information
N.C. Ristea, et. al., "Self-supervised predictive convolutional attentive block for anomaly detection", 2021, arXiv:2111.09099