发表机构
Dalhousie University（达尔豪斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对最后一层集成在函数空间多样性方面的问题，提出协方差最后一层集成方法，直接对成员激活施加协方差惩罚，恢复函数空间多样性，以低成本恢复深度集成的多样性和校准，还改进了OC分数，提升检测性能。
AI 中文摘要
最后一层集成（LLE）是一种高效的单通道方法，用于基于分布外（OOD）检测的基于分歧的认知不确定性。其弱点是成员共享骨干梯度，可能收敛到相同函数，导致信号依赖的成员间多样性丧失。本文提出协方差最后一层集成（cov-LLE），直接在函数空间中针对这种崩溃，对成员激活施加直接协方差惩罚。Cov-LLE恢复了权重正交性无法恢复的函数空间多样性，在匹配的K值下，以1倍骨干成本恢复了深度集成的大部分多样性和校准。将正交证书（OC）视为最后一层集成，还将检测器组织成两轴分类法，并揭示OC分数作为一个量级，激发了一个尺度不变、无标签的方向分数，修复其接近OOD的失败，在每个骨干上增加0.16到0.18的ROC AUC。
英文摘要
A Last-Layer Ensemble (LLE), $K$ linear units on one shared frozen feature map, is an efficient single-pass approach to the disagreement-based epistemic uncertainty for out-of-distribution (OOD) detection. Its weakness is that members share the backbone gradient and can converge toward the same function, collapsing the inter-member diversity the signal depends on. Whether last-layer diversity can be restored, and what mitigates the collapse, is an open question. The weight-orthonormality defining Orthonormal Certificates (OC), the weight-orthonormal special case of the LLE, is only an indirect correction; it decorrelates the weights of the members, not their predictions. Here, we instead target the collapse directly in function space, with a Covariance Last-Layer Ensemble (cov-LLE) that places a direct covariance penalty on member activations. Cov-LLE restores the function-space diversity that weight-orthonormality cannot, and at matched $K$ recovers much of the diversity and calibration of a deep ensemble at $1\times$ backbone cost (in-distribution prediction variance $0.05\!\to\!9.3$ vs. $22.1$ ($\times10^{-3}$), and ECE $0.135\!\to\!0.090$ vs. $0.035$, for a $K\times$-cost deep ensemble), at no cost to accuracy. Viewing OC as a last-layer ensemble also organizes detectors into a two-axis taxonomy (by how their units are trained and how their outputs are scored) and exposes the OC score as a magnitude, motivating a scale-invariant, label-free direction score that repairs its near-OOD failure, adding $+0.16$ to $+0.18$ ROC AUC on every backbone.
