Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909956811259904 |
|---|---|
| author | Xu, Guixian Li, Jinglai Tang, Junqi |
| author_facet | Xu, Guixian Li, Jinglai Tang, Junqi |
| contents | Equivariant Imaging (EI) regularization has become the de-facto technique for unsupervised training of deep imaging networks, without any need of ground-truth data. Observing that the EI-based unsupervised training paradigm currently has significant computational redundancy leading to inefficiency in high-dimensional applications, we propose a sketched EI regularization which leverages the randomized sketching techniques for acceleration. We apply our sketched EI regularization to develop an accelerated deep internal learning framework, which can be efficiently applied for test-time network adaptation. Additionally, for network adaptation tasks, we propose a parameter-efficient approach to accelerate both EI and Sketched-EI via optimizing only the normalization layers. Our numerical study on X-ray CT and multicoil magnetic resonance image reconstruction tasks demonstrate that our approach can achieve significant computational acceleration over the standard EI counterpart, especially in test-time training tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems Xu, Guixian Li, Jinglai Tang, Junqi Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Optimization and Control Equivariant Imaging (EI) regularization has become the de-facto technique for unsupervised training of deep imaging networks, without any need of ground-truth data. Observing that the EI-based unsupervised training paradigm currently has significant computational redundancy leading to inefficiency in high-dimensional applications, we propose a sketched EI regularization which leverages the randomized sketching techniques for acceleration. We apply our sketched EI regularization to develop an accelerated deep internal learning framework, which can be efficiently applied for test-time network adaptation. Additionally, for network adaptation tasks, we propose a parameter-efficient approach to accelerate both EI and Sketched-EI via optimizing only the normalization layers. Our numerical study on X-ray CT and multicoil magnetic resonance image reconstruction tasks demonstrate that our approach can achieve significant computational acceleration over the standard EI counterpart, especially in test-time training tasks. |
| title | Equivariant Test-Time Training with Operator Sketching for Imaging Inverse Problems |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2411.05771 |