Expansive Matching of Experts (EMOE) is a novel method that utilizes
support-expanding, extrapolatory pseudo-labeling to improve prediction and
uncertainty based rejection on out-of-distribution (OOD) points. We propose an
expansive data augmentation technique that generates OOD instances in a latent
space, and an empirical trial based approach to filter out augmented expansive
points for pseudo-labeling. EMOE utilizes a diverse set of multiple base
experts as pseudo-labelers on the augmented data to improve OOD performance
through a shared MLP with multiple heads (one per expert). We demonstrate that
EMOE achieves superior performance compared to state-of-the-art methods on
tabular data.

Expansive Matching of Experts (EMOE) 是一种利用支持扩展、外推伪标签方法来改善在分布外 (out-of-distribution) 点上的预测和基于不确定性的拒绝的新方法。我们提出了一种在潜在空间生成分布外实例的扩展数据增强技术，并基于经验的试验方法筛选出扩展点用于伪标签。EMOE 利用多个基础专家作为伪标签器，通过共享的多头 MLP（每个专家一个）在增强数据上改善分布外性能。我们证明，EMOE 在表格数据上实现了优于现有方法的性能。

EMOE：面向稳健的基于不确定性拒绝的专家扩展匹配

EMOE: Expansive Matching of Experts for Robust Uncertainty Based  Rejection

LiDAR-based semantic scene understanding is an important module in the modern
autonomous driving perception stack. However, identifying Out-Of-Distribution
(OOD) points in a LiDAR point cloud is challenging as point clouds lack
semantically rich features when compared with RGB images. We revisit this
problem from the perspective of selective classification, which introduces a
selective function into the standard closed-set classification setup. Our
solution is built upon the basic idea of abstaining from choosing any known
categories but learns a point-wise abstaining penalty with a marginbased loss.
Synthesizing outliers to approximate unlimited OOD samples is also critical to
this idea, so we propose a strong synthesis pipeline that generates outliers
originated from various factors: unrealistic object categories, sampling
patterns and sizes. We demonstrate that learning different abstaining
penalties, apart from point-wise penalty, for different types of (synthesized)
outliers can further improve the performance. We benchmark our method on
SemanticKITTI and nuScenes and achieve state-of-the-art results. Risk-coverage
analysis further reveals intrinsic properties of different methods. Codes and
models will be publicly available.

基于 LiDAR 的语义场景理解是现代自动驾驶感知系统中的一个重要模块。然而，LiDAR 点云中的区分开分布点 (OOD) 是具有挑战性的，因为与 RGB 图像相比，点云缺乏语义丰富的特征。我们从选择性分类的角度重新审视了这个问题，该分类在标准的封闭集分类设置中引入了一个选择性函数。我们的解决方案基于一种基本思想，即避免选择任何已知类别，而是以边际损失学习点处的避免惩罚。为了近似无限的 OOD 样本，合成异常点对于这个思想也至关重要，因此我们提出了一个强大的合成流程，可以生成来自各种因素的异常值：不真实的对象类别，采样模式和尺寸。我们证明了在不同类型（合成）异常值的不同点处避免惩罚可以进一步提高性能。我们在 SemanticKITTI 和 nuScenes 上对我们的方法进行了基准测试，并取得了最先进的结果。风险覆盖分析进一步揭示了不同方法的固有特性。代码和模型将公开提供。

点云异常检测的逐点弃权惩罚学习

Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection

Traditional training of deep classifiers yields overconfident models that are
not reliable under dataset shift. We propose a Bayesian framework to obtain
reliable uncertainty estimates for deep classifiers. Our approach consists of a
plug-in "generator" used to augment the data with an additional class of points
that lie on the boundary of the training data, followed by Bayesian inference
on top of features that are trained to distinguish these "out-of-distribution"
points.

使用贝叶斯框架在深度分类器上进行推理，从而获得可靠的不确定性估计。将一个生成器与基于边界点的特征组合起来，用于处理训练数据中的偏移问题。