Preliminary Results on Distribution Shift Performance of Deep Networks for Synthetic Aperture Sonar Classification

Isaac D. Gerg, Vishal Monga

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

3 Scopus citations

Abstract

We demonstrate the ease by which deep networks are fooled by sonar-relevant distribution shifts induced by sonar-relevant transforms, imaging errors common to SAS, and unseen target/background combinations. Furthermore, the generated images fooling the networks are trivial for human operators to interpret. We posit this disconnect between human and machine performance is an open area of research and, when reconciled, improves human-machine trust. Our goal with this work is to begin discerning where deep network performance (specifically convolutional neural networks (CNNs)) deteriorates and how their perception model differs from humans. Specifically, we show network performance varies widely across contemporary architectures and training schemes on: (1) images derived from a set of sonar-relevant transformations, which we call semantically stable, (2) imagery perturbed with quadratic phase error (common to SAS), and (3) a synthetic target dataset created by injecting real targets into unseen real backgrounds. Finally, we delineate the relationship between spatial frequency and network performance and find many networks rely almost exclusively on low-frequency content to make their predictions. These results may help illuminate why changes to a sonar system or simulation sometimes necessitate complete network retraining to accommodate the 'new' data; a time consuming process. Consequently, we hope this work stimulates future research bridging the gap between human and machine perception in the space of automated SAS image interpretation.

Original languageEnglish (US)
Title of host publicationOCEANS 2022 Hampton Roads
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665468091
DOIs
StatePublished - 2022
Event2022 OCEANS Hampton Roads, OCEANS 2022 - Hampton Roads, United States
Duration: Oct 17 2022Oct 20 2022

Publication series

NameOceans Conference Record (IEEE)
Volume2022-October
ISSN (Print)0197-7385

Conference

Conference2022 OCEANS Hampton Roads, OCEANS 2022
Country/TerritoryUnited States
CityHampton Roads
Period10/17/2210/20/22

All Science Journal Classification (ASJC) codes

  • Oceanography
  • Ocean Engineering

Fingerprint

Dive into the research topics of 'Preliminary Results on Distribution Shift Performance of Deep Networks for Synthetic Aperture Sonar Classification'. Together they form a unique fingerprint.

Cite this