面向少样本语义分割的贝叶斯分解与语义补全
Bayesian Decomposition and Semantic Completion for Few-shot Semantic Segmentation
将少样本分割分解为先验、似然和类一致性三项，并用轻量类无关定位模型并行评估 SAM 生成的碎片区域，把分割转化为二分类；这种贝叶斯分解思路和语义补全模块可复用于其他基于 SAM 的开放词表分割任务。
原文依据 we propose a Bayesian Probabilistic Network (BPNet) that reformulates FSS as a composition of three interpretable components
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本语义分割（FSS）旨在仅给定少量标注示例的情况下分割新类别的对象。然而，现有方法通常依赖复杂的类别特定建模，导致计算成本高且在低数据条件下泛化能力有限。为解决这些挑战，我们提出了一种贝叶斯概率网络（BPNet），将 FSS 重新表述为三个可解释组件的组合：先验、似然和类一致性项。具体而言，采用高效的 Segment Anything Model（SAM）为查询图像生成碎片化的先验区域，而似然和一致性项均由轻量级的类无关定位模型（CALM）估计。CALM 通过二分类检测头同时预测支持集-查询集对之间的类一致性，并通过在支持图像中定位目标区域来估计似然。通过并行评估 SAM 生成的区域，CALM 能够高效地识别核心区域，从而将分割问题转化为简单的二分类任务。此外，为缓解 SAM 提议的语义不完整性，我们引入了一个基于注意力的语义补全模块（SCM），该模块利用局部和全局上下文线索将碎片化区域整合为语义完整的掩码。大量实验表明，BPNet 在保持高效率的同时达到了最优性能。
英文原文摘要 1495 字符
Few-shot Semantic Segmentation (FSS) aims to segment objects of novel categories given only a handful of labeled examples. However, existing methods often rely on complex category-specific modeling, resulting in high computational cost and limited generalization under low-data regimes. To address these challenges, we propose a Bayesian Probabilistic Network (BPNet) that reformulates FSS as a composition of three interpretable components: a prior, a likelihood, and a class-consistency term. Specifically, an efficient Segment Anything Model (SAM) is employed to generate fragmented prior regions for the query image, while both the likelihood and the consistency terms are estimated by a lightweight Class-Agnostic Localization Model (CALM). CALM simultaneously predicts the class consistency between support-query pairs through a binary classification head and estimates the likelihood by localizing the target region in the support image. By evaluating SAM-generated regions in parallel, CALM can efficiently identify the core region, thereby transforming the segmentation problem into a simple binary classification task. Furthermore, to mitigate the semantic incompleteness of SAM proposals, we introduce an attention-based Semantic Completion Module (SCM), which leverages local and global context cues to integrate fragmented regions into semantically complete masks. Extensive experiments demonstrate that BPNet achieves state-of-the-art performance while maintaining high efficiency.