EXPLAINABLE SYSTEMATIC ANALYSIS FOR SYNTHETIC APERTURE SONAR IMAGERY

被引：2

作者：

Walker, Sarah ^{[1
]}

Peeples, Joshua ^{[1
]}

Dale, Jeff ^{[2
]}

Keller, James ^{[2
]}

Zarel, Alina ^{[1
]}

机构：

[1] Univ Florida, Elect & Comp Engn, Gainesville, FL 32611 USA

[2] Univ Missouri, Comp Sci & Elect Engn, Columbia, MO 65211 USA

来源：

2021 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM IGARSS | 2021年

基金：

美国国家科学基金会;

关键词：

deep learning; transfer learning; SAS; classification; XAI; CLASSIFICATION; INFORMATION;

D O I：

10.1109/IGARSS47720.2021.9554901

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

In this work, we present an in-depth and systematic analysis using tools such as local interpretable model-agnostic explanations (LIME) [1] and divergence measures to analyze what changes lead to improvement in performance in fine tuned models for synthetic aperture sonar (SAS) data. We examine the sensitivity to factors in the fine tuning process such as class imbalance. Our findings show not only an improvement in seafloor texture classification, but also provide greater insight into what features play critical roles in improving performance as well as a knowledge of the importance of balanced data for fine tuning deep learning models for seafloor classification in SAS imagery.

引用

页码：2835 / 2838

页数：4

共 12 条

[1] Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].

Adadi, Amina ;

Berrada, Mohammed .

IEEE ACCESS, 2018, 6 :52138-52160

[2] A systematic study of the class imbalance problem in convolutional neural networks [J].

Buda, Mateusz ;

Maki, Atsuto ;

Mazurowski, Maciej A. .

NEURAL NETWORKS, 2018, 106 :249-259

[3] Possibilistic Context Identification for SAS Imagery [J].

Du, Xiaoxiao ;

Zare, Alina ;

Cobb, J. Tory .

DETECTION AND SENSING OF MINES, EXPLOSIVE OBJECTS, AND OBSCURED TARGETS XX, 2015, 9454

[4] TEXTONS, THE ELEMENTS OF TEXTURE-PERCEPTION, AND THEIR INTERACTIONS [J].

JULESZ, B .

NATURE, 1981, 290 (5802) :91-97

[5]

Julesz B., 1962, Information Theory, IRE Transactions on, V8, P84

[6] From BoW to CNN: Two Decades of Texture Representation for Texture Classification [J].

Liu, Li ;

Chen, Jie ;

Fieguth, Paul ;

Zhao, Guoying ;

Chellappa, Rama ;

Pietikainen, Matti .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2019, 127 (01) :74-109

[7] Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J].

Ojala, T ;

Pietikäinen, M ;

Mäenpää, T .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) :971-987

[8]

Principe JC, 2010, INFORM SCI STAT, P1, DOI 10.1007/978-1-4419-1570-2

[9] "Why Should I Trust You?" Explaining the Predictions of Any Classifier [J].

Ribeiro, Marco Tulio ;

Singh, Sameer ;

Guestrin, Carlos .

KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :1135-1144

[10] Exploiting Environmental Information for Improved Underwater Target Classification in Sonar Imagery [J].

Williams, David P. ;

Fakiris, Elias .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (10) :6284-6297

← 1 2 →