SAR Image Classification Using Few-Shot Cross-Domain Transfer Learning
By Mohammad Rostami, Soheil Kolouri, Eric Eaton, Kyungnam Kim. 2019
61 citations recorded by the source corpus.
Data-driven classification algorithms based on deep convolutional neural networks have reached human-level performance for many tasks within Electro-Optical (EO) computer vision. Despite being the prevailing visual sensory data, EO imaging is not effective in applications such as environmental monitoring at extended periods, where data collection at occluded weather is necessary. Synthetic Aperture Radar (SAR) is an effective imaging tool to circumvent these limitations and collect visual sensory information continually. However, replicating the success of deep learning on SAR domains is not straightforward. This is mainly because training deep networks requires huge labeled datasets and data labeling is a lot more challenging in SAR domains. We develop an algorithm to transfer knowledge from EO domains to SAR domains to eliminate the need for huge labeled data points in the SAR domains. Our idea is to learn a shared domain-invariant embedding for cross-domain knowledge transfer such that the embedding is discriminative for two related EO and SAR tasks, while the latent data distributions for both domains remain similar. As a result, a classifier learned using mostly EO data can generalize well on the related task for the SAR domain.
Subfields: Aerospace Engineering, Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
In Artificial Intelligence
- Mohammad Rostami
- Wael AbdAlmageed
- Mohamed E. Hussein
- Leonidas Spinoulas
- Joe Mathai
- Soheil Kolouri
- Kyungnam Kim
- Phillip E. Pope
Citations in the corpus
- Detection and Continual Learning of Novel Face Presentation Attacks (2021, background): “The model then needs to be retrained from scratch (or fine-tuned) on the augmented dataset [26].”
- Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment (2019, background): “This is due to the fact that the Wasserstein distance between two onedimensional probability distributions has a closed form solution and is equal to the lp-distance between the inverse of their cumulative distribution functions Since only samples from distributions are available, the onedimensional”
- Learning Transferable Knowledge Through Embedding Spaces (2019, unknown): “Results of this chapter have been presented in [142; 143; 144; 145].”