Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery

TL;DR

This paper proposes a novel cross-modality anomaly detection method for remote sensing imagery that leverages large-margin learning and anomaly simulation to enable zero-shot detection across diverse modalities.

Contribution

It introduces a theoretically grounded large-margin deviation metric learning framework with anomaly simulation for effective cross-modality anomaly detection.

Findings

Achieves zero-shot detection in five modalities including hyperspectral and SAR.

Proposes large-margin losses for pixel and feature-level deviation ranking.

Demonstrates improved transferability over existing anomaly detectors.

Abstract

Remote sensing anomaly detector can find the objects deviating from the background as potential targets for Earth monitoring. Given the diversity in earth anomaly types, designing a transferring model with cross-modality detection ability should be cost-effective and flexible to new earth observation sources and anomaly types. However, the current anomaly detectors aim to learn the certain background distribution, the trained model cannot be transferred to unseen images. Inspired by the fact that the deviation metric for score ranking is consistent and independent from the image distribution, this study exploits the learning target conversion from the varying background distribution to the consistent deviation metric. We theoretically prove that the large-margin condition in labeled samples ensures the transferring ability of learned deviation metric. To satisfy this condition, two large margin losses for pixel-level and feature-level deviation ranking are proposed respectively. Since the real anomalies are difficult to acquire, anomaly simulation strategies are designed to compute the model loss. With the large-margin learning for deviation metric, the trained model achieves cross-modality detection ability in five modalities including hyperspectral, visible light, synthetic aperture radar (SAR), infrared and low-light in zero-shot manner.