Article
Version 1
Preserved in Portico This version is not peer-reviewed
Deep Transfer Learning for Few-shot SAR Image Classification
Version 1
: Received: 1 May 2019 / Approved: 6 May 2019 / Online: 6 May 2019 (06:28:04 CEST)
A peer-reviewed article of this Preprint also exists.
Rostami, M.; Kolouri, S.; Eaton, E.; Kim, K. Deep Transfer Learning for Few-Shot SAR Image Classification. Remote Sens. 2019, 11, 1374. Rostami, M.; Kolouri, S.; Eaton, E.; Kim, K. Deep Transfer Learning for Few-Shot SAR Image Classification. Remote Sens. 2019, 11, 1374.
Abstract
Reemergence of deep Neural Networks (CNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is possible because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be a lot more challenging and for various reasons using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper,we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data is easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other learning competing approaches.
Keywords
transfer learning; convolutional neural network; electro-optical imaging; synthetic aperture radar (SAR) imaging; optimal transport metric
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment