arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.08049cs.CV
收藏

SphOR:从表示学习角度看待开放集识别以在深度学习模型中识别未知类别

SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models

The University of Melbourne(墨尔本大学)

Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge

AI总结:

SphOR通过监督表示学习和三个创新技术提升开放集识别性能,实现最先进的AUROC和OSCR结果。

摘要:

在安全关键和现实应用中依赖基于深度神经网络(DNN)的分类器,需要开放集识别(OSR)。OSR能够识别在训练期间未知的输入数据,而不是将它们误分类为已知类别。DNN由特征提取主干和分类头组成;然而,大多数OSR方法通常联合训练这两个组件,通常导致适应性差的特征表示。其他方法使用现成的目标,如监督对比学习,这些目标并非专门针对OSR设计。为了解决这些限制,我们提出了SpHOR,通过监督表示学习显式地塑造特征空间,然后训练分类器。与依赖通用特征学习不同,SpHOR通过三个关键创新来为OSR定制表示学习:(1)通过正交标签嵌入强制区分类别的特征,确保类别之间更清晰的分离。(2)施加球形约束,将表示建模为von Mises-Fisher分布的混合。(3)将Mixup和标签平滑(LS)直接整合到表示学习阶段。为了量化这些技术如何增强OSR的表示,我们引入了两个指标:角分离性(AS)和范数分离性(NS)。结合所有三个创新,SpHOR在各种粗粒度和细粒度开放集基准上实现了最先进的结果(在AUROC和OSCR上),特别是在语义偏移基准上,改进高达5.1%。代码见https://github.com/nadarasarbahavan/SpHOR

英文摘要:

The reliance on Deep Neural Network (DNN)-based classifiers in safety-critical and real-world applications necessitates Open-Set Recognition (OSR). OSR enables the identification of input data from classes unknown during training as unknown, as opposed to misclassifying them as belonging to a known class. DNNs consist of a feature extraction backbone and classifier head; however, most OSR methods typically train both components jointly, often yielding feature representations that adapt poorly to unknown data. Other approaches employ off-the-shelf objectives, such as supervised contrastive learning, which are not specifically designed for OSR. To address these limitations, we propose SpHOR, which explicitly shapes the feature space via supervised representation learning, before training a classifier. Instead of relying on generic feature learning, SpHOR custom-designs representation learning for OSR through three key innovations: (1) enforcing discriminative class-specific features via orthogonal label embeddings, ensuring clearer separation between classes. (2) imposing a spherical constraint, modeling representations as a mixture of von Mises-Fisher distributions. (3) integrating Mixup and Label Smoothing (LS) directly into the representation learning stage. To quantify how these techniques enhance representations for OSR, we introduce two metrics: the Angular Separability (AS) and Norm Separability (NS). Combining all three innovations, SpHOR achieves state-of-the-art results (in AUROC and OSCR) across various coarse-grained and fine-grained open-set benchmarks, particularly excelling on the Semantic Shift Benchmark with improvements up to 5.1\%. Code at https://github.com/nadarasarbahavan/SpHOR

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑