Test-Time Adaptation via Style and Structure Guidance for Histological Image Registration
Abstract
Image registration plays a crucial role in histological image analysis, encompassing tasks like multi-modality fusion and disease grading. Traditional registration methods optimize objective functions for each image pair, yielding reliable accuracy but demanding heavy inference burdens. Recently, learning-based registration methods utilize networks to learn the optimization process during training and apply a one-step forward process during testing. While these methods offer promising registration performance with reduced inference time, they remain sensitive to appearance variances and local structure changes commonly encountered in histological image registration scenarios. In this paper, for the first time, we propose a novel test-time adaptation method for histological image registration, aiming to improve the generalization ability of learning-based methods. Specifically, we design two operations, style guidance and shape guidance, for the test-time adaptation process. The former leverages style representations encoded by feature statistics to address the issue of appearance variances, while the latter incorporates shape representations encoded by HOG features to improve registration accuracy in regions with structural changes. Furthermore, we consider the continuity of the model during the test-time adaptation process. Different from the previous methods initialized by a given trained model, we introduce a smoothing strategy to leverage historical models for better generalization. We conduct experiments with several representative learning-based backbones on the public histological dataset, demonstrating the superior registration performance of our test-time adaptation method.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? cites Tent: Fully Test-Time Adaptation by Entropy Minimization
- TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? cites Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
- Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models cites Tent: Fully Test-Time Adaptation by Entropy Minimization
- Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models cites Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
- Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models cites Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
- Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization cites Tent: Fully Test-Time Adaptation by Entropy Minimization
Cited by top-tier papers1
Builds on5
- Tent: Fully Test-Time Adaptation by Entropy MinimizationDequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno A. Olshausen et al.ICLR 2021 · 1,731 citations
- Test-Time Training with Self-Supervision for Generalization under Distribution ShiftsYu Sun, Xiaolong Wang, Zhuang Liu, John Miller et al.ICML 2020 · 1,220 citations
- TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?Yuejiang Liu, Parth Kothari, Bastien van Delft, Baptiste Bellot-Gurlet et al.NeurIPS 2021 · 469 citations
- Test-Time Classifier Adjustment Module for Model-Agnostic Domain GeneralizationYusuke Iwasawa, Yutaka MatsuoNeurIPS 2021 · 456 citations
- Recursive Cascaded Networks for Unsupervised Medical Image RegistrationShengyu Zhao, Yue Dong, Eric I-Chao Chang, Yan XuICCV 2019 · 289 citations
Related papers
- TANGO: Learning Distribution-wise Foundation Prior Consistency and Instance-wise Style Calibration for Medical Image GeneralizationChuang Liu, Yichao Cao, Xiu Su, Haogang ZhuCVPR 2026
- Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image SegmentationXingguo Lv, Xingbo Dong, Liwen Wang, Jiewen Yang et al.CVPR 2025
- Gradient Alignment Improves Test-Time Adaptation for Medical Image SegmentationZiyang Chen, Yiwen Ye, Yongsheng Pan, Yong XiaAAAI 2025 · 12 citations
- Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary LearningAhmed Hatem, Yiming Qian, Yang WangICCV 2023 · 28 citations
- Progressive Test Time Energy Adaptation for Medical Image SegmentationXiaoran Zhang, Byung-Woo Hong, Hyoungseob Park, Daniel H. Pak et al.ICCV 2025 · 1 citation
