TAX：多标注语义分割的倾向和分配解释器
TAX: Tendency-and-Assignment Explainer for Semantic Segmentation with Multi-Annotators
摘要：
为了理解神经网络执行分类预测的深度，最近的研究关注点一直集中在开发技术以提供理想的解释。然而，大多数现有的方法不能很容易地应用于语义分割，而且，他们的目的不是提供多注释器设置下的可解释性。而不是查看地面实况像素级标签注释由一个单一的注释者一致的标签趋势，我们的目标是提供可解释的语义分割，并回答两个关键而又实际的问题：“谁”有助于产生的分割，以及“为什么”这样的分配是确定的。在本文中，我们提出了一个学习框架的倾向和分配解释器（TAX），旨在提供注释和分配水平的可解释性。更具体地说，我们学习卷积核子集，用于对每种类型的注释的标记趋势进行建模，同时联合观察原型库，为学习上述内核提供视觉指导。为了进行评估，我们考虑了具有多注释器的合成和真实世界数据集。我们表明，我们的税收可以应用到国家的最先进的网络架构具有可比的性能，而在这两个级别的分割可解释性可以相应地提供。
英文摘要：
To understand how deep neural networks perform classification predictions, recent research attention has been focusing on developing techniques to offer desirable explanations. However, most existing methods cannot be easily applied for semantic segmentation; moreover, they are not designed to offer interpretability under the multi-annotator setting. Instead of viewing ground-truth pixel-level labels annotated by a single annotator with consistent labeling tendency, we aim at providing interpretable semantic segmentation and answer two critical yet practical questions: "who" contributes to the resulting segmentation, and "why" such an assignment is determined. In this paper, we present a learning framework of Tendency-and-Assignment Explainer (TAX), designed to offer interpretability at the annotator and assignment levels. More specifically, we learn convolution kernel subsets for modeling labeling tendencies of each type of annotation, while a prototype bank is jointly observed to offer visual guidance for learning the above kernels. For evaluation, we consider both synthetic and real-world datasets with multi-annotators. We show that our TAX can be applied to state-of-the-art network architectures with comparable performances, while segmentation interpretability at both levels can be offered accordingly.
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。
