用双曲嵌入提升异常样本检测能力，天然支持层级泛化。
Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors
- 设计平衡双曲学习算法，优化层次扭曲与子层级均衡
- 13个数据集上超越现有异常检测方法，性能更优
- 适合需要层级结构感知的异常检测场景
异常分布识别是深度学习中的重要问题，旨在过滤模型训练分布之外的样本。本文结论简洁：良好的层次化双曲嵌入更适用于区分分布内与分布外样本。我们提出平衡双曲学习（Balanced Hyperbolic Learning），设计一种联合优化层次扭曲与浅层/宽层子层级平衡的双曲类别嵌入算法。随后将类别嵌入作为双曲原型用于分布内数据分类，并拓展现有异常评分函数以适配双曲原型。在13个数据集和13种评分函数上的实证评估表明，我们的双曲嵌入在相同数据与骨干网络下优于现有异常检测方法。同时，其性能超越其他双曲方法，击败先进对比学习方法，并原生支持层级异常泛化。
原文摘要 · Abstract (English)
Out-of-distribution recognition forms an important and well-studied problem in deep learning, with the goal to filter out samples that do not belong to the distribution on which a network has been trained. The conclusion of this paper is simple: a good hierarchical hyperbolic embedding is preferred for discriminating in- and out-of-distribution samples. We introduce Balanced Hyperbolic Learning. We outline a hyperbolic class embedding algorithm that jointly optimizes for hierarchical distortion and balancing between shallow and wide subhierarchies. We then use the class embeddings as hyperbolic prototypes for classification on in-distribution data. We outline how to generalize existing out-of-distribution scoring functions to operate with hyperbolic prototypes. Empirical evaluations across 13 datasets and 13 scoring functions show that our hyperbolic embeddings outperform existing out-of-distribution approaches when trained on the same data with the same backbones. We also show that our hyperbolic embeddings outperform other hyperbolic approaches, beat state-of-the-art contrastive methods, and natively enable hierarchical out-of-distribution generalization.
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。