Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Jingtao, Wang, Xinyu, Zhao, Hengwei, Zhang, Liangpei, Zhong, Yanfei
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910596699521024
author Li, Jingtao
Wang, Xinyu
Zhao, Hengwei
Zhang, Liangpei
Zhong, Yanfei
author_facet Li, Jingtao
Wang, Xinyu
Zhao, Hengwei
Zhang, Liangpei
Zhong, Yanfei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07511
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery
Li, Jingtao
Wang, Xinyu
Zhao, Hengwei
Zhang, Liangpei
Zhong, Yanfei
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
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.
title Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2310.07511