发表机构
The University of Melbourne（墨尔本大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对开放集识别中标签平滑系数固定不变的问题，提出SmoothOperator，依据样本显著性动态调整平滑系数，以最小开销集成至四种球形表示学习方法，在语义偏移基准上AUROC、OSCR和闭集准确率提升最高达4.7%。
AI 中文摘要
开放集识别（OSR）旨在使模型能够准确分类已知类别，同时拒绝来自未见类别的样本。OSR中的一个关键挑战在于训练期间无法对未知类别的无界分布进行建模，这常常导致这些类别的样本被错误分类。与其对未知类别建模，近期工作转而塑造特征空间，使已知类别紧凑且分离良好，球形表示学习方法已通过这种方式取得了强劲结果。标签平滑已被确定为这一成功的关键驱动因素之一，然而它对每个训练样本应用相同的系数，无论每个样本已被嵌入得多好。我们表明，OSR中使用的球形表示学习目标共享一种对齐-均匀性结构，其中标签仅通过对齐项进入。因此，标签平滑充当对齐拨盘，而固定系数将该拨盘设置为每个样本的相同值。我们提出了一种即插即用的方法，SmoothOperator（SmoothOP），它根据每个样本的“显著性”（一种嵌入空间信号，用于衡量样本自身类别相对于其最强竞争类别的突出程度）来设置其平滑系数。我们的方法以最小的训练开销集成到四种现有的球形表示学习方法中。SmoothOP为具有高显著性的样本分配强平滑，这减少了它们的对齐并放松了它们的拉动。在语义偏移基准上，SmoothOP增强的变体通常在数据集、语义偏移程度和OSR后处理器上优于其基础目标，在AUROC、OSCR和闭集准确率上提升高达4.7%。
英文摘要
Open Set Recognition (OSR) aims to enable models to accurately classify known classes while rejecting samples from unseen classes. A key challenge in OSR lies in the inability to model the unbounded distribution of unknown classes during training, often leading to the misclassification of samples from these classes. Rather than modeling unknowns, recent work shapes the feature space so that known classes are compact and well separated, and spherical representation learning methods have achieved strong results this way. Label smoothing has been identified as one of the key drivers of this success, yet it applies the same coefficient to every training sample, regardless of how well each sample is already embedded. We show that the spherical representation learning objectives used in OSR share a single alignment--uniformity structure in which labels enter only through the alignment term. Label smoothing therefore acts as an alignment dial, and a fixed coefficient sets this dial to the same value for every sample. We propose a plug-in, SmoothOperator (SmoothOP), which sets the smoothing coefficient of each sample from its \textbf{prominence}, an embedding-space signal measuring how clearly the sample's own class stands out against its strongest competing class. Our method integrates into four existing spherical representation learning methods at minimal training overhead. SmoothOP assigns strong smoothing to samples with high prominence, which reduces their alignment and relaxes their pull. On the Semantic Shift Benchmark, SmoothOP-augmented variants generally outperform their base objectives across datasets, degrees of semantic shift, and OSR post-processors, with gains of up to 4.7\% in AUROC, OSCR, and closed-set accuracy.
