TY - GEN
T1 - Fast Adaptation of Radar Detection via Online Meta-learning
AU - Khan, Zareen
AU - Jiang, Wei
AU - Haimovich, Alexander
AU - Govoni, Mark
AU - Garner, Timothy
AU - Simeone, Osvaldo
N1 - Funding Information:
Research was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-20-2-0219. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper addresses the problem of continual learning of radar detectors from sequentially provided training data. Given a limited number of labeled samples for each of a number of tasks in a certain class, a model-agnostic meta-learning (MAML) approach is developed to enable few-shot learning of a new task in the class. In the radar detection problem, a task is associated with a set of specific environmental conditions such as target, clutter or interference properties. The proposed detector design is separated into two stages: a meta-training stage and an adaptation stage. The outcome of the meta-training stage is used to initialize the learning of the detector parameter vector, which in turn relies on the training data available for adaptation. Unlike a previously proposed offline approach, where all data available for meta-training was assumed available upfront, the proposed learning procedure is applied online, where meta-training data is made available incrementally, with each task. Numerical results validate that the proposed detector may learn a new task from a limited number of labeled samples, and that the performance improves as the meta-training relies on an increasing number of tasks.
AB - This paper addresses the problem of continual learning of radar detectors from sequentially provided training data. Given a limited number of labeled samples for each of a number of tasks in a certain class, a model-agnostic meta-learning (MAML) approach is developed to enable few-shot learning of a new task in the class. In the radar detection problem, a task is associated with a set of specific environmental conditions such as target, clutter or interference properties. The proposed detector design is separated into two stages: a meta-training stage and an adaptation stage. The outcome of the meta-training stage is used to initialize the learning of the detector parameter vector, which in turn relies on the training data available for adaptation. Unlike a previously proposed offline approach, where all data available for meta-training was assumed available upfront, the proposed learning procedure is applied online, where meta-training data is made available incrementally, with each task. Numerical results validate that the proposed detector may learn a new task from a limited number of labeled samples, and that the performance improves as the meta-training relies on an increasing number of tasks.
KW - Radar detection
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85150193253&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85150193253&partnerID=8YFLogxK
U2 - 10.1109/IEEECONF56349.2022.10051849
DO - 10.1109/IEEECONF56349.2022.10051849
M3 - Conference contribution
AN - SCOPUS:85150193253
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 580
EP - 585
BT - 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022
Y2 - 31 October 2022 through 2 November 2022
ER -