Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.11196 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911442168446976 |
|---|---|
| author | Zhang, Hongyang Zhang, Haitao Liu, Yinhao Lin, Kunjie Huang, Yue Ding, Xinghao |
| author_facet | Zhang, Hongyang Zhang, Haitao Liu, Yinhao Lin, Kunjie Huang, Yue Ding, Xinghao |
| contents | Radar signal recognition in open electromagnetic environments is challenging due to diverse operating modes and unseen radar types. Existing methods often overlook position relations in pulse sequences, limiting their ability to capture semantic dependencies over time. We propose RadarPos, a position-aware self-supervised framework that leverages pulse-level temporal dynamics without complex augmentations or masking, providing improved position relation modeling over contrastive learning or masked reconstruction. Using this framework, we evaluate cross-mode radar signal recognition under the long-tailed setting to assess adaptability and generalization. Experimental results demonstrate enhanced discriminability and robustness, highlighting practical applicability in real-world electromagnetic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11196 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Position-Aware Self-supervised Representation Learning for Cross-mode Radar Signal Recognition Zhang, Hongyang Zhang, Haitao Liu, Yinhao Lin, Kunjie Huang, Yue Ding, Xinghao Signal Processing Artificial Intelligence Machine Learning Radar signal recognition in open electromagnetic environments is challenging due to diverse operating modes and unseen radar types. Existing methods often overlook position relations in pulse sequences, limiting their ability to capture semantic dependencies over time. We propose RadarPos, a position-aware self-supervised framework that leverages pulse-level temporal dynamics without complex augmentations or masking, providing improved position relation modeling over contrastive learning or masked reconstruction. Using this framework, we evaluate cross-mode radar signal recognition under the long-tailed setting to assess adaptability and generalization. Experimental results demonstrate enhanced discriminability and robustness, highlighting practical applicability in real-world electromagnetic environments. |
| title | Position-Aware Self-supervised Representation Learning for Cross-mode Radar Signal Recognition |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.11196 |