SAUGE：驯服SAM以实现不确定性对齐的多粒度边缘检测
SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection
AI总结：
本文提出SAUGE，利用SAM中间特征的多粒度特性，通过轻量模块回归不同层特征以对齐边缘标签的不确定性，实现灵活多粒度边缘检测，并在多个数据集上验证了优越性与泛化性。
摘要：
边缘标签通常因标注者的不同偏好而处于各种粒度水平，因此处理逐像素标签的主观性一直是边缘检测的焦点。以往的方法常采用简单的投票策略来减弱这种标签不确定性，或对标签施加预定义分布（如高斯分布）的强假设。在本工作中，我们揭示了分割一切模型（SAM）为建模边缘标签中的不确定性提供了强大的先验知识。我们的关键洞察在于，SAM的中间特征本质上对应于不同粒度下的物体边缘，这反映了因不确定性而产生的不同边缘选项。因此，我们尝试通过将来自不同层的SAM中间特征回归到多粒度级别的物体边缘，来使不确定性与粒度对齐。通过这种方式，模型能够以数据驱动的方式充分且明确地探索多样的“不确定性”。具体而言，我们将一个轻量级模块（约1.5%的额外参数）注入冻结的SAM中，以逐步融合并调整其中间特征，从而从粗到细地估计边缘。至关重要的是，需要归一化人类边缘标签的粒度水平，以匹配其固有的不确定性。为此，我们简单地对现有的真实边缘标签进行线性混合，以创建具有不同粒度的伪标签。因此，我们的不确定性对齐边缘检测器能够灵活地在任何期望的粒度（包括最优粒度）下产生边缘。得益于SAM，我们的模型独特地展示了跨数据集边缘检测的强大泛化能力。在BSDS500、Multicue和NYUDv2上的大量实验结果验证了我们模型的优越性。
英文摘要：
Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse ``uncertainties'' in a data-driven fashion. Specifically, we inject a lightweight module (~ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model's superiority.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
