Skeleton-Guided Progressive Test-Time Adaptation for Thin Curvilinear Structures

Key points

• 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.1
• To address this, we propose Skeleton-Guided Progressive Test-Time Adaptation (SGP-TTA).1
• 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.1
• Extensive experiments show that SGP-TTA consistently outperforms existing TTA methods in topological connectivity, with the largest margins under cross-modality shift.1

Sources (1)

• [1]Skeleton-Guided Progressive Test-Time Adaptation for Thin Curvilinear Structures
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:19 AM

  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.

Extractive summary: sentences quoted from the sources.