用多编码器扩散模型融合检测分布外数据，效果更好且参数少2.3倍。
Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection
- 通过各编码器的表示空间扩散模型，融合检测多种分布偏移。
- 在四种偏移类型上均达到≥0.94的AUROC，参数量仅为基线的1/2.3。
- 无需分布外标签，可自动识别编码器专长，适合多模态系统部署。
我们通过多编码器表示空间扩散模型（RDMs）的融合，解决全谱分布偏移下的分布外（OOD）检测问题——包括全局域变化、语义差异、纹理不同和协变量损坏。仅从正常数据中统计识别各编码器对特定偏移类型的敏感性，提出无监督的两层最小门控机制EncMin2L，结合并校准各编码器的扩散似然检测器，无需分布外标签，在参数量降低2.3倍的情况下优于单一多编码器基线。两种仅基于正常数据的诊断指标：η²（类条件F检验）与Δμ（合成扰动下的对数似然偏移），量化编码器专长；通过蒂佩特最小值法组合各编码器得分，生成稳定校准的分布外信号。EncMin2L在所有四种偏移类型上均实现≥0.94的AUROC，超越现有代表空间扩散模型的最先进检测器，在重叠基准上表现优异。
原文摘要 · Abstract (English)
We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture differences, and covariate corruptions -- through a multi-encoder fusion of per-encoder representation-space diffusion models (RDMs). We statistically identify each encoder's sensitivity to specific shift types from ID data alone and introduce EncMin2L -- an encoder-agnostic two-level $\min(\cdot)$-gate that combines and calibrates per-encoder diffusion-based likelihood detectors without OOD labels, outperforming monolithic multi-encoder baselines at $2.3\times$ lower parameter cost. Two ID-data diagnostics: $η^2$ (class-conditional F-test) and $Δμ$ (log-likelihood shift under synthetic corruptions) -- quantify encoder specialization, while a Tippett minimum $p$-value combination aggregates per-encoder scores into a single, calibration-stable OOD signal. EncMin2L achieves $\geq 0.94$ AUROC across all four shift types simultaneously, outperforming the state-of-the-art representation-space diffusion OOD detectors across overlapping benchmarks.
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。