Abstract
This work introduces an attention mechanism that can be integrated into any standard convolution neural network (CNN) to improve model sensitivity and prediction accuracy with minimal computational overhead. We introduce the attention mechanism in a lightweight network-Alexnet and evaluate its classification performance for human micro-Doppler signatures. We show that the Alexnet model trained with an attention module can implicitly learn to highlight the salient regions in the radar signatures whilst suppressing the irrelevant background regions and consistently improve the network predictions by more than 4% in most cases. We further provide network visualizations through class activation mapping, providing better insights into how the predictions are made.
Original language | English |
---|---|
Title of host publication | International Conference on Radar Systems (RADAR 2022) |
Place of Publication | Edinburgh |
Publisher | Institution of Engineering and Technology |
Pages | 190-195 |
Number of pages | 6 |
Volume | 2022 |
ISBN (Print) | 978-1-83953-777-6 |
DOIs | |
Publication status | Published - 24 Oct 2022 |
Event | International Conference on Radar Systems 2022 - Murrayfield Stadium, Edinburgh, United Kingdom Duration: 24 Oct 2022 → 27 Oct 2022 https://radar2022.theiet.org/ |
Conference
Conference | International Conference on Radar Systems 2022 |
---|---|
Abbreviated title | RADAR 2022 |
Country/Territory | United Kingdom |
City | Edinburgh |
Period | 24/10/22 → 27/10/22 |
Internet address |
Keywords
- Radar Sensing
- Attention Networks
- Deep Learning
- Micro-Doppler Signatures
- Human Activity Recognition