AnoDFDNet: A Deep Feature Difference Network for Anomaly Detection

TL;DR

This paper introduces AnoDFDNet, a novel deep learning approach that detects anomalies by comparing pairs of images over time using a combination of CNNs and Vision Transformers, outperforming traditional single-image methods.

Contribution

The paper presents a new anomaly detection framework that focuses on difference detection between image pairs, leveraging deep feature differences with CNNs and Vision Transformers, which is a novel approach in this domain.

Findings

Demonstrated superior performance on three diverse datasets.

Effectively detects anomalies like foreign objects and oil leaks.

Outperforms existing single-image anomaly detection methods.

Abstract

This paper proposed a novel anomaly detection (AD) approach of High-speed Train images based on convolutional neural networks and the Vision Transformer. Different from previous AD works, in which anomalies are identified with a single image using classification, segmentation, or object detection methods, the proposed method detects abnormal difference between two images taken at different times of the same region. In other words, we cast anomaly detection problem with a single image into a difference detection problem with two images. The core idea of the proposed method is that the 'anomaly' usually represents an abnormal state instead of a specific object, and this state should be identified by a pair of images. In addition, we introduced a deep feature difference AD network (AnoDFDNet) which sufficiently explored the potential of the Vision Transformer and convolutional neural networks. To verify the effectiveness of the proposed AnoDFDNet, we collected three datasets, a difference dataset (Diff Dataset), a foreign body dataset (FB Dataset), and an oil leakage dataset (OL Dataset). Experimental results on above datasets demonstrate the superiority of proposed method. Source code are available at https://github.com/wangle53/AnoDFDNet.