Robust Satellite Image Classification with Bayesian Deep Learning

Yutian Pang, Sheng Cheng, Jueming Hu, Yongming Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Image-based object detection and classification are essential for satellite-based monitoring, which spans multiple safety-critical engineering applications. Meanwhile, state-of-the-art deep learning significant improves the accuracy for image classification tasks thus has been deployed in various scenarios. However, it's well-known deep learning-based image classifiers are vulnerable to small perturbations along specific directions, known as adversarial attacks. These attacks are exceptionally effective to fool image classifiers. In extreme cases, merely one pixel's change can lead to a attacker-desired wrong prediction label. In this work, we show that deep learning with Bayesian formulation can extend the deep learning adversarial robustness by a large margin, without the need of adversarial training. Moreover, we show that the stochastic classifier after the deterministic CNN extractor has sufficient robustness enhancement rather than a stochastic feature extractor before the stochastic classifier. This advises on utilizing stochastic layers in building decision-making pipelines within a safety-critical domain. Additionally, we show that the Bayesian posterior can act as the safety precursor of ongoing malicious activities towards a deployed image classification system. This leads to the detection of adversarial samples in cybersecurity. With lots of potentials, we leave them as the future studies.

Original languageEnglish (US)
Title of host publication2022 Integrated Communication, Navigation and Surveillance Conference, ICNS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665484190
DOIs
StatePublished - 2022
Event2022 Integrated Communication, Navigation and Surveillance Conference, ICNS 2022 - Dulles, United States
Duration: Apr 5 2022Apr 7 2022

Publication series

NameIntegrated Communications, Navigation and Surveillance Conference, ICNS
Volume2022-April
ISSN (Print)2155-4943
ISSN (Electronic)2155-4951

Conference

Conference2022 Integrated Communication, Navigation and Surveillance Conference, ICNS 2022
Country/TerritoryUnited States
CityDulles
Period4/5/224/7/22

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Robust Satellite Image Classification with Bayesian Deep Learning'. Together they form a unique fingerprint.

Cite this