Translator Disclaimer
Presentation + Paper
21 April 2021 Convolutional and generative pairing for SAR cross-target transfer learning
Author Affiliations +
Machine learning systems are known to require large amounts of data to effectively generalize. When this data isn’t available, synthetically generated data is often used in its place. With synthetic aperture radar (SAR) imagery, the domain shift required to effectively transfer knowledge from simulated to measured imagery is non-trivial. We propose a pairing of convolutional networks (CNNs) with generative adversarial networks (GANs) to learn an effective mapping between the two domains. Classification networks are trained individually on measured and synthetic data, then a mapping between layers of the two CNNs is learned using a GAN.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alexander Jennison, Benjamin Lewis, Ashley DeLuna, and Jonathan Garrett "Convolutional and generative pairing for SAR cross-target transfer learning", Proc. SPIE 11728, Algorithms for Synthetic Aperture Radar Imagery XXVIII, 1172805 (21 April 2021);

Back to Top