用门控机制提升模型对不确定性的多模态建模，单次推理即可更准确识别异常样本。
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
- 设计门控证据混合模型，通过能量信号动态调节证据输出，实现距离感知的自适应抑制。
- 在CIFAR-10上将误差率降低至6.81（原14.27），分类准确率提升至93.75%，显著改善校准性。
- 无需多轮推断即可捕捉多重认知不确定性，适合高可靠性场景如医疗诊断与自动驾驶。
证据深度学习（EDL）通过预测狄利克雷证据实现单次推理下的不确定性估计，但常出现过度自信、校准不佳，且难以表示多模态认知不确定性。本文提出门控证据混合（GEM）模型家族，学习模型内能量信号，并以距离感知方式端到端地控制证据输出。GEM-CORE 在特征层面学习能量并生成有界门控，支持不足时平滑抑制证据；GEM-MIX 通过轻量级证据头混合与可学习路由权重，在不依赖多轮集成的前提下捕捉认知多模态性；GEM-FI 引入费雪信息正则化，稳定混合分配，减少头部坍缩，提升边界不确定性平滑度。在图像分类与分布外检测基准测试中，GEM 实现了更优的校准性与内部/外部样本分离能力。在CIFAR-10上，相比DAEDL，GEM-FI将准确率从91.11提升至93.75（+2.64个百分点），布里尔分数降低至6.81（原14.27，-7.46），误分类检测的AUPR从99.08提升至99.94（+0.86）。在认知型分布外检测任务中，于CIFAR-10→SVHN和CIFAR-10→CIFAR-100上分别达到AUPR/AUROC为92.59/95.09和90.20/89.06，优于DAEDL的85.54/89.30与88.19/86.10。
原文摘要 · Abstract (English)
Evidential Deep Learning (EDL) enables single-pass uncertainty estimation by predicting Dirichlet evidence, but it can remain overconfident and poorly calibrated, and it often fails to represent multi-modal epistemic uncertainty. We introduce Gated Evidential Mixtures (GEM), a family of models that learns an in-model energy signal and uses it to gate evidential outputs end-to-end in a distance-informed manner. GEM-CORE learns a feature-level energy and maps it to a bounded gate that smoothly suppresses evidence when support is low. To capture epistemic multi-modality without multi-pass ensembling, GEM-MIX adds a lightweight mixture of evidential heads with learned routing weights while preserving single-pass inference. Finally, GEM-FI stabilizes mixture allocations via a Fisher-informed regularizer, reducing head collapse and producing smoother boundary uncertainty. Across image classification and OOD detection benchmarks, GEM improves calibration and ID/OOD separation with single-pass inference. On CIFAR-10, GEM-FI vs. DAEDL improves accuracy from 91.11 to 93.75 (+2.64 pp), reduces Brier x100 from 14.27 to 6.81 (-7.46), and also improves misclassification-detection AUPR from 99.08 to 99.94 (+0.86). For epistemic OOD detection, GEM-FI achieves AUPR/AUROC of 92.59/95.09 on CIFAR-10 to SVHN and 90.20/89.06 on CIFAR-10 to CIFAR-100, compared with 85.54/89.30 and 88.19/86.10 for DAEDL.
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。