This paper aims to address few-shot segmentation. While existing prototype-based methods have achieved considerable success, they suffer from uncertainty and ambiguity caused by limited labeled examples. In this work, we propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. The probabilistic modeling of the prototype enhances the model's generalization ability by handling the inherent uncertainty caused by limited data and intra-class variations of objects. To further enhance the model, we introduce a local latent variable to represent the attention map of each query image, which enables the model to attend to foreground objects while suppressing the background. The optimization of the proposed model is formulated as a variational Bayesian inference problem, which is established by amortized inference networks. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods. We also provide comprehensive analyses and ablation studies to gain insight into the effectiveness of our method for few-shot segmentation.

翻译：本文旨在解决少样本分割问题。现有基于原型的方法虽已取得显著成功，但由于标记样本有限，这些方法存在不确定性和模糊性。本研究提出注意力原型推理（API），一种用于少样本分割的概率潜变量框架。我们定义全局潜变量来表示每个目标类别的原型，并将其建模为概率分布。原型的概率建模通过处理有限数据与类内差异导致的内在不确定性，增强了模型的泛化能力。为进一步提升模型性能，我们引入局部潜变量来表示每张查询图像的注意力图，使模型能够聚焦前景目标并抑制背景。所提模型的优化被表述为变分贝叶斯推理问题，并通过摊销推理网络实现。我们在四个基准数据集上进行了广泛实验，结果表明我们提出的方法在性能上至少与最先进的基于原型的方法相当，且常优于后者。我们还提供了全面的分析与消融研究，以深入理解该方法在少样本分割任务中的有效性。