用最优传输度量分布差异，提升对域外数据的检测能力。
Prototype-based Optimal Transport for Out-of-Distribution Detection
- 通过最优传输计算测试样本与类内原型的分布距离
- 结合虚拟异常点增强对邻近类内数据的域外识别
- 适合需要高可靠性推理的部署场景
检测域外（OOD）输入对于提升深度神经网络在真实部署中的可靠性至关重要。本文受ID与OOD数据间固有分布偏移的启发，提出一种新方法：利用最优传输度量测试输入与已知类别原型之间的分布差异。由此产生的传输成本可量化每个测试样本对整体差异的贡献，作为理想的OOD检测指标。为解决仅依赖与原型的传输成本难以识别靠近ID数据的域外样本的问题，我们通过线性外推生成虚拟异常点以逼近域外区域。将测试样本到原型的传输成本与到虚拟异常点的成本相结合，强化了对靠近ID数据的域外样本的识别，从而提升ID与OOD样本的区分能力。实验表明，该方法优于当前最先进方法。
原文摘要 · Abstract (English)
Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes. The resulting transport costs are used to quantify the individual contribution of each test input to the overall discrepancy, serving as a desirable measure for OOD detection. To address the issue that solely relying on the transport costs to ID prototypes is inadequate for identifying OOD inputs closer to ID data, we generate virtual outliers to approximate the OOD region via linear extrapolation. By combining the transport costs to ID prototypes with the costs to virtual outliers, the detection of OOD data near ID data is emphasized, thereby enhancing the distinction between ID and OOD inputs. Experiments demonstrate the superiority of our method over state-of-the-art methods.
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。