Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.25755 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916037686984704 |
|---|---|
| author | Scharf, Maximilian Trenti, Marco Bock, Felix Davidson, Padraig Brosch, Tobias de Miranda, Benjamin Rodrigues Huber, Sigurd Felser, Timo |
| author_facet | Scharf, Maximilian Trenti, Marco Bock, Felix Davidson, Padraig Brosch, Tobias de Miranda, Benjamin Rodrigues Huber, Sigurd Felser, Timo |
| contents | SAR image classification naturally has to deal with huge noise and a high dynamic range particularly requiring robust classification models. Additionally, the deployment of these models on edge devices, such as drones and military aircraft, requires a careful balance between model size and classification accuracy. This study explores the potential of tensor networks to meet these robustness requirements, specifically evaluating their resilience to data poisoning. Unlike previous works that concentrated on conventional neural networks for SAR object detection, this research focuses on the robustness and model reduction capabilities of tensor networks in object classification. Our findings indicate that tensor networks are adept at addressing both the challenges of robustness and the need for model efficiency, thereby contributing valuable insights to the ongoing discourse in radar applications and deep learning methodologies in general. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25755 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Quantum-Inspired Robust and Scalable SAR Object Classification Scharf, Maximilian Trenti, Marco Bock, Felix Davidson, Padraig Brosch, Tobias de Miranda, Benjamin Rodrigues Huber, Sigurd Felser, Timo Quantum Physics Computer Vision and Pattern Recognition Computational Physics SAR image classification naturally has to deal with huge noise and a high dynamic range particularly requiring robust classification models. Additionally, the deployment of these models on edge devices, such as drones and military aircraft, requires a careful balance between model size and classification accuracy. This study explores the potential of tensor networks to meet these robustness requirements, specifically evaluating their resilience to data poisoning. Unlike previous works that concentrated on conventional neural networks for SAR object detection, this research focuses on the robustness and model reduction capabilities of tensor networks in object classification. Our findings indicate that tensor networks are adept at addressing both the challenges of robustness and the need for model efficiency, thereby contributing valuable insights to the ongoing discourse in radar applications and deep learning methodologies in general. |
| title | Quantum-Inspired Robust and Scalable SAR Object Classification |
| topic | Quantum Physics Computer Vision and Pattern Recognition Computational Physics |
| url | https://arxiv.org/abs/2604.25755 |