DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories
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_ | 1866929727369904128 |
|---|---|
| author | Cheng, Hongzhe Zheng, Tianyou Zhang, Tianyi Johnson-Roberson, Matthew Zhi, Weiming |
| author_facet | Cheng, Hongzhe Zheng, Tianyou Zhang, Tianyi Johnson-Roberson, Matthew Zhi, Weiming |
| contents | Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability of diffusion models to OOD detection, existing approaches are limited to Euclidean or latent image spaces. Our work extends OOD detection to trajectories in the Special Euclidean Group in 3D ($\mathbb{SE}(3)$), addressing a critical need in computer vision, robotics, and engineering applications that process object pose sequences in $\mathbb{SE}(3)$. We present $\textbf{D}$iffusion-based $\textbf{O}$ut-of-distribution detection on $\mathbb{SE}(3)$ ($\mathbf{DOSE3}$), a novel OOD framework that extends diffusion to a unified sample space of $\mathbb{SE}(3)$ pose sequences. Through extensive validation on multiple benchmark datasets, we demonstrate $\mathbf{DOSE3}$'s superior performance compared to state-of-the-art OOD detection frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories Cheng, Hongzhe Zheng, Tianyou Zhang, Tianyi Johnson-Roberson, Matthew Zhi, Weiming Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Out-of-Distribution(OOD) detection, a fundamental machine learning task aimed at identifying abnormal samples, traditionally requires model retraining for different inlier distributions. While recent research demonstrates the applicability of diffusion models to OOD detection, existing approaches are limited to Euclidean or latent image spaces. Our work extends OOD detection to trajectories in the Special Euclidean Group in 3D ($\mathbb{SE}(3)$), addressing a critical need in computer vision, robotics, and engineering applications that process object pose sequences in $\mathbb{SE}(3)$. We present $\textbf{D}$iffusion-based $\textbf{O}$ut-of-distribution detection on $\mathbb{SE}(3)$ ($\mathbf{DOSE3}$), a novel OOD framework that extends diffusion to a unified sample space of $\mathbb{SE}(3)$ pose sequences. Through extensive validation on multiple benchmark datasets, we demonstrate $\mathbf{DOSE3}$'s superior performance compared to state-of-the-art OOD detection frameworks. |
| title | DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectories |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.16725 |