Anti-coherence 正则化绝对缩放方法用于 OOD 检测
Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection
AI 导读
一篇 arXiv 论文提出针对 OOD 检测的改进方法：修复 SCALE 方法在负激活下比例失定义的问题，用绝对值激活计算缩放比（Absolute Fix），并加入 Anti-coherence 正则化，惩罚预测类别中符号不匹配的 max-logit 贡献。
正文 · 原文
Abstract:Out-of-distribution (OOD) detection is recognized as a critical problem in AI safety. SCALE is an effective post-hoc OOD detection method in the activation-shaping family that requires no training data and rescales penultimate activations using a percentile-based magnitude ratio. However, this ratio is ill-defined when negative activations are present, since positive and negative contributions cancel within the underlying sum, causing SCALE to degenerate on backbones such as ViT. We address this with an Absolute Fix that computes the ratio over absolute-valued activations rather than discarding negative activations through ReLU. Building on this corrected scale, we propose Anti-coherence regularization, which penalizes the scaling factor by the fraction of a sample's max-logit contributions to the max logit that are sign-mismatched and thereby suppresses unreliable evidence for the predicted class. Despite requiring no access to training data or training labels, our method ties or outperforms activation-shaping methods that rely on training data in terms of AUROC and FPR@95 on CIFAR-10 and ImageNet under the OpenOOD v1.5 protocol.
| Comments: | 29 pages, 6 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32255 [cs.LG] |
| (or arXiv:2610.32255v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32255 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Donghwan Kim [view email]
[v1]
Fri, 23 Oct 2026 07:09:51 UTC (4,220 KB)
来源：arXiv cs.AI · arxiv.org