基于层次结构的分布外检测，让模型判断异常样本属于哪个类别分支。
ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
- 利用多层级网络构建概率模型，识别分布外样本在类别树中的位置
- 在三个带层级结构的数据集上实现精准分类，提升对异常样本的语义定位能力
- 适合需要理解异常样本来源的场景，如医疗诊断、自动驾驶
深度学习中的分布外（OOD）检测传统上被视为二分类任务：样本要么属于已知类别，要么被标记为分布外，而较少关注分布外样本与已知类别之间的语义关系。本文提出一种框架，用于在给定类别层次结构下检测并分类分布外样本。具体而言，目标是将分布外数据预测到类别层次结构的正确内部节点，而已知的分布内（ID）类别则应被预测为其对应的叶节点。该方法利用类别层次结构构建概率模型，并通过在多个层次深度上训练的网络实现。我们在三个具有预定义类别层次结构的数据集上进行实验，验证了该方法的有效性。代码已开源：https://github.com/walline/prohoc。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic relationships between OOD samples and the in-distribution (ID) classes. We propose a framework for detecting and classifying OOD samples in a given class hierarchy. Specifically, we aim to predict OOD data to their correct internal nodes of the class hierarchy, whereas the known ID classes should be predicted as their corresponding leaf nodes. Our approach leverages the class hierarchy to create a probabilistic model and we implement this model by using networks trained for ID classification at multiple hierarchy depths. We conduct experiments on three datasets with predefined class hierarchies and show the effectiveness of our method. Our code is available at https://github.com/walline/prohoc.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。