ECCV

Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models

超越类别子空间：用于单域模型中可靠分布外检测的教师引导训练

Hong Yang, Devroop Kar, Qi Yu, Travis Desell, Alex Ororbia

AI总结 本文提出教师引导训练方法，通过蒸馏多域教师模型的残差结构，提升单域模型在分布外检测中的可靠性，显著降低远OOD的误检率，同时保持在域性能。

Comments 14 pages main text, 22 pages appendix; under review at ECCV 2026