Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yi, Zhao, Yidong, Tao, Qian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912985107136512
author Zhang, Yi
Zhao, Yidong
Tao, Qian
author_facet Zhang, Yi
Zhao, Yidong
Tao, Qian
contents Deformable image registration remains a central challenge in medical image analysis, particularly under multi-modal scenarios where intensity distributions vary significantly across scans. While deep learning methods provide efficient feed-forward predictions, they often fail to generalize robustly under distribution shifts at test time. A straightforward remedy is full network fine-tuning, yet for modern architectures such as Transformers or deep U-Nets, this adaptation is prohibitively expensive in both memory and runtime when operating in 3D. Meanwhile, the naive fine-tuning struggles more with potential degradation in performance in the existence of drastic domain shifts. In this work, we propose a registration framework that integrates a frozen pretrained \textbf{mono-modal} registration model with a lightweight adaptation pipeline for \textbf{multi-modal} image registration. Specifically, we employ style transfer based on contrast-agnostic representation generation and refinement modules to bridge modality and domain gaps with instance optimization at test time. This design is orthogonal to the choice of backbone mono-modal model, thus avoids the computational burden of full fine-tuning while retaining the flexibility to adapt to unseen domains. We evaluate our approach on the Learn2Reg 2025 LUMIR validation set and observe consistent improvements over the pretrained state-of-the-art mono-modal backbone. In particular, the method ranks second on the multi-modal subset, third on the out-of-domain subset, and achieves fourth place overall in Dice score. These results demonstrate that combining frozen mono-modal models with modality adaptation and lightweight instance optimization offers an effective and practical pathway toward robust multi-modal registration.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26393
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization
Zhang, Yi
Zhao, Yidong
Tao, Qian
Image and Video Processing
Computer Vision and Pattern Recognition
Deformable image registration remains a central challenge in medical image analysis, particularly under multi-modal scenarios where intensity distributions vary significantly across scans. While deep learning methods provide efficient feed-forward predictions, they often fail to generalize robustly under distribution shifts at test time. A straightforward remedy is full network fine-tuning, yet for modern architectures such as Transformers or deep U-Nets, this adaptation is prohibitively expensive in both memory and runtime when operating in 3D. Meanwhile, the naive fine-tuning struggles more with potential degradation in performance in the existence of drastic domain shifts. In this work, we propose a registration framework that integrates a frozen pretrained \textbf{mono-modal} registration model with a lightweight adaptation pipeline for \textbf{multi-modal} image registration. Specifically, we employ style transfer based on contrast-agnostic representation generation and refinement modules to bridge modality and domain gaps with instance optimization at test time. This design is orthogonal to the choice of backbone mono-modal model, thus avoids the computational burden of full fine-tuning while retaining the flexibility to adapt to unseen domains. We evaluate our approach on the Learn2Reg 2025 LUMIR validation set and observe consistent improvements over the pretrained state-of-the-art mono-modal backbone. In particular, the method ranks second on the multi-modal subset, third on the out-of-domain subset, and achieves fourth place overall in Dice score. These results demonstrate that combining frozen mono-modal models with modality adaptation and lightweight instance optimization offers an effective and practical pathway toward robust multi-modal registration.
title Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.26393