利用最优传输边界生成模糊样本，抑制模型对异常输入的过度自信。
Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
- 通过最优传输构造语义模糊区域的边界样本
- 在边界附近采样得到几何合理的异常输入，显著降低过自信率
- 适合需要提升模型可靠性与鲁棒性的实际应用场景
深度神经网络在分布外（OOD）输入上常产生过度自信的预测，影响其在开放世界环境中的可靠性。半离散最优传输（OT）中的奇点标记了语义模糊区域，分类器在此类区域容易做出无根据的高置信度预测。受此启发，我们提出一种基于OT几何结构的框架，以缓解OOD过自信问题。具体地，我们将连续基分布与训练数据的潜在嵌入进行OT建模，识别出相应的奇异边界。通过在这些边界附近采样，构建一类称为最优传输诱导的分布外样本（OTIS）的新类型异常输入，其具有几何合理性且本质语义模糊。训练时，在OTIS上施加置信度抑制损失，引导模型在结构不确定区域作出更校准的预测。大量实验表明，该方法显著缓解了OOD过自信现象，并优于现有最先进方法。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) often produce overconfident predictions on out-of-distribution (OOD) inputs, undermining their reliability in open-world environments. Singularities in semi-discrete optimal transport (OT) mark regions of semantic ambiguity, where classifiers are particularly prone to unwarranted high-confidence predictions. Motivated by this observation, we propose a principled framework to mitigate OOD overconfidence by leveraging the geometry of OT-induced singular boundaries. Specifically, we formulate an OT problem between a continuous base distribution and the latent embeddings of training data, and identify the resulting singular boundaries. By sampling near these boundaries, we construct a class of OOD inputs, termed optimal transport-induced OOD samples (OTIS), which are geometrically grounded and inherently semantically ambiguous. During training, a confidence suppression loss is applied to OTIS to guide the model toward more calibrated predictions in structurally uncertain regions. Extensive experiments show that our method significantly alleviates OOD overconfidence and outperforms 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。