FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908865664122880 |
|---|---|
| author | Jena, Rohit Chaudhari, Pratik Gee, James C. |
| author_facet | Jena, Rohit Chaudhari, Pratik Gee, James C. |
| contents | The paper proposes FireANTs, a multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. Existing state-of-the-art methods for diffeomorphic image matching are slow due to inefficient implementations and slow convergence due to the ill-conditioned nature of the optimization problem. Deep learning methods offer fast inference but require extensive training time, substantial inference memory, and fail to generalize across long-tailed distributions or diverse image modalities, necessitating costly retraining. We address these challenges by proposing a training-free, GPU-accelerated multi-scale Adaptive Riemannian Optimization algorithm for fast and accurate dense diffeomorphic image matching. FireANTs runs about 2.5x faster than ANTs on a CPU, and upto 1200x faster on a GPU. On a single GPU, FireANTs performs competitively with deep learning methods on inference runtime while consuming upto 10x less memory. FireANTs shows remarkable robustness to a wide variety of matching problems across modalities, species, and organs without any domain-specific training or tuning. Our framework allows hyperparameter grid search studies with significantly less resources and time compared to traditional and deep learning registration algorithms alike. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01249 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching Jena, Rohit Chaudhari, Pratik Gee, James C. Computer Vision and Pattern Recognition The paper proposes FireANTs, a multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. Existing state-of-the-art methods for diffeomorphic image matching are slow due to inefficient implementations and slow convergence due to the ill-conditioned nature of the optimization problem. Deep learning methods offer fast inference but require extensive training time, substantial inference memory, and fail to generalize across long-tailed distributions or diverse image modalities, necessitating costly retraining. We address these challenges by proposing a training-free, GPU-accelerated multi-scale Adaptive Riemannian Optimization algorithm for fast and accurate dense diffeomorphic image matching. FireANTs runs about 2.5x faster than ANTs on a CPU, and upto 1200x faster on a GPU. On a single GPU, FireANTs performs competitively with deep learning methods on inference runtime while consuming upto 10x less memory. FireANTs shows remarkable robustness to a wide variety of matching problems across modalities, species, and organs without any domain-specific training or tuning. Our framework allows hyperparameter grid search studies with significantly less resources and time compared to traditional and deep learning registration algorithms alike. |
| title | FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.01249 |