Skip to content
Hot eventLive

SGP-TTA:骨架引导的渐进式测试时适应

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv(Computer Vision,一手来源)报道提出 Skeleton-Guided Progressive Test-Time Adaptation(SGP-TTA),用于细曲线结构分割。该方法包含两个核心机制:ProgBN 按样本数量调度,将归一化从冻结的源统计逐步转向目标估计;CSR 从几何对齐的多视角预测导出结构目标,并仅更新 BN 仿射参数以保持连通性。实验显示,SGP-TTA 在拓扑连通性上持续优于现有 TTA 方法,在跨模态迁移时优势最大。目前报道未涉及后续验证或争议。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Computer Vision
    SGP-TTA:骨架引导的渐进式测试时自适应方法

    提出 Skeleton-Guided Progressive Test-Time Adaptation(SGP-TTA),用于细曲线结构分割。ProgBN 按样本数量调度把归一化从冻结源统计逐步转向目标估计,CSR 从几何对齐的多视角预测导出结构目标并仅更新 BN 仿射参数以保持连通性。实验显示其在拓扑连通性上持续优于现有 TTA 方法,跨模态迁移时优势最大。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.