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.

翻译：我们通过多编码器融合各编码器的表征空间扩散模型（RDMs），解决了全谱分布偏移——包括全局域变化、语义分歧、纹理差异和协变量损坏——下的分布外（OOD）检测问题。我们仅从同分布（ID）数据中统计识别每个编码器对特定偏移类型的敏感度，并引入编码器无关的两级 $\min(\cdot)$ 门控机制EncMin2L——该机制在无需OOD标签的情况下组合并校准基于似然的逐编码器扩散探测器，以 $2.3\times$ 更低的参数成本超越单一多编码器基线。两种ID数据诊断方法：$\eta^2$（类别条件F检验）和 $\Delta\mu$（合成损坏下的对数似然偏移）量化了编码器特化程度，而蒂皮特最小 $p$ 值组合法将各编码器分数聚合为单个校准稳定的OOD信号。EncMin2L在所有四种偏移类型上同时达到 $\geq 0.94$ AUROC，在重叠基准测试中超越了最先进的表征空间扩散OOD探测器。