Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper introduces Skeleton-Guided Progressive Test-Time Adaptation (SGP-TTA) to address the catastrophic failures of existing test-time adaptation methods on thin curvilinear structures under severe cross-modality domain shifts. SGP-TTA employs Progressive Batch Normalization to dynamically balance source and target statistics and Consensus Skeleton Recall to enforce topological connectivity by updating only BN affine parameters. Experimental results demonstrate SGP-TTA's superior performance in maintaining structural integrity, particularly under extreme domain gaps.
Thin structure segmentation breaks under cross-modality shifts, but a novel TTA approach preserves topology by aligning multi-view predictions and progressively adapting normalization statistics.
Accurate segmentation of thin curvilinear structures is vital for various real-world applications, from vessel analysis to road extraction. Yet their intricate geometry makes even minor pixel-wise errors enough to break the global topology, and this structural fragility turns severe domain shifts into catastrophic failures. The difficulty is most acute under cross-modality gaps, where the imaging process itself differs fundamentally between source and target. While test-time adaptation (TTA) offers a practical source-free remedy, existing methods adapt feature statistics and confidence, neither of which constrains connectivity, and thus degrade under such extreme gaps. To address this, we propose Skeleton-Guided Progressive Test-Time Adaptation (SGP-TTA). Progressive Batch Normalization (ProgBN) shifts normalization from frozen source statistics toward current target estimates under a sample-count schedule, so that the source-target balance follows the stage of adaptation rather than a fixed coefficient. Consensus Skeleton Recall (CSR) then derives a structural target from geometrically aligned multi-view predictions and updates only the BN affine parameters to preserve connected structures. Extensive experiments show that SGP-TTA consistently outperforms existing TTA methods in topological connectivity, with the largest margins under cross-modality shift. The project page is available at https://boa-jang.github.io/SGP-TTA.