通过提前注入高频信息提升图像模型对分布外样本的识别能力
Early High-Frequency Injection for Geometry-Sensitive OOD Detection
- 在输入阶段提前注入高频信号，改变特征几何结构
- 在CIFAR-100和ImageNet-100上分别实现最佳平均FPR95和次优AUROC
- 特别适用于依赖几何结构的分布外检测任务
后训练的分布外（OOD）检测器依赖于训练中已编码的表示几何结构。我们通过对CE、SimCLR、SupCon及面向OOD的PALM方法进行分频带的MMD²分析发现，低频输入成分导致的ID/OOD特征差异较弱，而高频成分则提供更强的可分性。这一观察启发了早期高频注入（EIHF）方法：在首个卷积层前无须修改训练目标地注入高频信息。实验表明，在匹配训练与评分设置下，EIHF能重塑类别条件特征几何结构，显著降低ID/OOD马氏距离得分重叠。在CIFAR-100和ImageNet-100上的测试显示，其在CIFAR-100上性能领先，在ImageNet-100上实现最优平均FPR95与次优平均AUROC；但在场景中心的Places数据偏移中表现受限。代码已公开。
原文摘要 · Abstract (English)
Post-hoc OOD detectors score logits or features after training, so their success depends on the geometry already encoded in the representation. We revisit this assumption through a band-wise MMD^2 analysis across CE, SimCLR, SupCon, and the OOD-oriented representation method PALM. In our diagnostic, low-frequency input bands induce weaker ID/OOD feature discrepancy, whereas higher-frequency bands tend to provide stronger separability. This observation motivates EIHF, an input-side intervention that exposes high-frequency evidence before the first convolution without changing the training objective. EIHF is strongest for geometry-sensitive OOD detection: under matched training and scoring settings, it reshapes class-conditional feature geometry and reduces ID/OOD Mahalanobis score overlap. Experiments on CIFAR-100 and ImageNet-100 show gains on CIFAR-100 and the best average FPR95 with second-best average AUROC on ImageNet-100, while also revealing a limitation on the scene-centric Places shift. Code is available at https://anonymous.4open.science/r/EIHF.
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。