Saved in:
Bibliographic Details
Main Authors: Lallouet, Noé, Cazenave, Tristan, Enderli, Cyrille, Gourdin, Stéphanie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908425321971712
author Lallouet, Noé
Cazenave, Tristan
Enderli, Cyrille
Gourdin, Stéphanie
author_facet Lallouet, Noé
Cazenave, Tristan
Enderli, Cyrille
Gourdin, Stéphanie
contents Recent research works establish deep neural networks as high performing tools for radar target detection, especially on challenging environments (presence of clutter or interferences, multi-target scenarii...). However, the usually large computational complexity of these networks is one of the factors preventing them from being widely implemented in embedded radar systems. We propose to investigate novel neural architecture search (NAS) methods, based on Monte-Carlo Tree Search (MCTS), for finding neural networks achieving the required detection performance and striving towards a lower computational complexity. We evaluate the searched architectures on endoclutter radar signals, in order to compare their respective performance metrics and generalization properties. A novel network satisfying the required detection probability while being significantly lighter than the expert-designed baseline is proposed.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21772
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search
Lallouet, Noé
Cazenave, Tristan
Enderli, Cyrille
Gourdin, Stéphanie
Signal Processing
Machine Learning
Recent research works establish deep neural networks as high performing tools for radar target detection, especially on challenging environments (presence of clutter or interferences, multi-target scenarii...). However, the usually large computational complexity of these networks is one of the factors preventing them from being widely implemented in embedded radar systems. We propose to investigate novel neural architecture search (NAS) methods, based on Monte-Carlo Tree Search (MCTS), for finding neural networks achieving the required detection performance and striving towards a lower computational complexity. We evaluate the searched architectures on endoclutter radar signals, in order to compare their respective performance metrics and generalization properties. A novel network satisfying the required detection probability while being significantly lighter than the expert-designed baseline is proposed.
title Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2506.21772