通过线性化与参数扰动，实现测试时的可靠不确定性估计。
TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation
- 基于训练过程的线性化动态，建模参数扰动的影响。
- 在图像分类大尺度基准上达到当前最优，尤其擅长近分布样本。
- 无需重新训练，适合部署于需要安全检测的开放世界场景。
可靠的不确定性估计是许多现代分布外（OOD）检测器的基础，对深度学习模型在开放世界中的安全部署至关重要。本文提出TULiP，一种理论驱动的后处理不确定性估计方法，用于OOD检测。该方法考虑网络在收敛前施加的假设扰动，基于线性化训练动态，推导出此类扰动的效应上界，从而可通过扰动模型参数计算出不确定性得分。最终，不确定性由一组采样预测结果得出。我们在合成回归和分类数据集上可视化该上界，并在大规模图像分类的OOD检测基准上验证了TULiP的有效性。实验表明，该方法在近分布样本上表现尤为出色，整体性能达到当前最优水平。
原文摘要 · Abstract (English)
A reliable uncertainty estimation method is the foundation of many modern out-of-distribution (OOD) detectors, which are critical for safe deployments of deep learning models in the open world. In this work, we propose TULiP, a theoretically-driven post-hoc uncertainty estimator for OOD detection. Our approach considers a hypothetical perturbation applied to the network before convergence. Based on linearized training dynamics, we bound the effect of such perturbation, resulting in an uncertainty score computable by perturbing model parameters. Ultimately, our approach computes uncertainty from a set of sampled predictions. We visualize our bound on synthetic regression and classification datasets. Furthermore, we demonstrate the effectiveness of TULiP using large-scale OOD detection benchmarks for image classification. Our method exhibits state-of-the-art performance, particularly for near-distribution samples.
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。