Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909830724190208 |
|---|---|
| author | Lekhak, Sagar Ientilucci, Emmett J. Dera, Dimah Ghosh, Susmita |
| author_facet | Lekhak, Sagar Ientilucci, Emmett J. Dera, Dimah Ghosh, Susmita |
| contents | Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial attacks, leading to missed detection or misclassification. This study introduces the idea of uncertainty quantification through Monte Carlo (MC) Dropout, integrated into a fine-tuned ResNet-50 architecture for surface landmine and UXO classification, which was tested on a simulated dataset. Integrating the MC Dropout approach helps quantify epistemic uncertainty, providing an additional metric for prediction reliability, which could be helpful to make more informed decisions in demining operations. Experimental results on clean, adversarially perturbed, and noisy test images demonstrate the model's ability to flag unreliable predictions under challenging conditions. This proof-of-concept study highlights the need for uncertainty quantification in demining, raises awareness about the vulnerability of existing neural networks in demining to adversarial threats, and emphasizes the importance of developing more robust and reliable models for practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06238 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout Lekhak, Sagar Ientilucci, Emmett J. Dera, Dimah Ghosh, Susmita Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Other Statistics Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial attacks, leading to missed detection or misclassification. This study introduces the idea of uncertainty quantification through Monte Carlo (MC) Dropout, integrated into a fine-tuned ResNet-50 architecture for surface landmine and UXO classification, which was tested on a simulated dataset. Integrating the MC Dropout approach helps quantify epistemic uncertainty, providing an additional metric for prediction reliability, which could be helpful to make more informed decisions in demining operations. Experimental results on clean, adversarially perturbed, and noisy test images demonstrate the model's ability to flag unreliable predictions under challenging conditions. This proof-of-concept study highlights the need for uncertainty quantification in demining, raises awareness about the vulnerability of existing neural networks in demining to adversarial threats, and emphasizes the importance of developing more robust and reliable models for practical applications. |
| title | Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Other Statistics |
| url | https://arxiv.org/abs/2510.06238 |