Novelty detection is a critical task for deploying machine learning models in the open world. A crucial property of novelty detection methods is universality, which can be interpreted as generalization across various distributions of training or test data. More precisely, for novelty detection, distribution shifts may occur in the training set or the test set. Shifts in the training set refer to cases where we train a novelty detector on a new dataset and expect strong transferability. Conversely, distribution shifts in the test set indicate the methods' performance when the trained model encounters a shifted test sample. We experimentally show that existing methods falter in maintaining universality, which stems from their rigid inductive biases. Motivated by this, we aim for more generalized techniques that have more adaptable inductive biases. In this context, we leverage the fact that contrastive learning provides an efficient framework to easily switch and adapt to new inductive biases through the proper choice of augmentations in forming the negative pairs. We propose a novel probabilistic auto-negative pair generation method AutoAugOOD, along with contrastive learning, to yield a universal novelty detector method. Our experiments demonstrate the superiority of our method under different distribution shifts in various image benchmark datasets. Notably, our method emerges universality in the lens of adaptability to different setups of novelty detection, including one-class, unlabeled multi-class, and labeled multi-class settings. Code: https://github.com/mojtaba-nafez/UNODE

翻译：新颖性检测是在开放世界中部署机器学习模型的关键任务。新颖性检测方法的一个重要特性是通用性，这可以理解为对不同训练或测试数据分布的泛化能力。更准确地说，对于新颖性检测，分布偏移可能发生在训练集或测试集中。训练集的分布偏移指我们在新数据集上训练新颖性检测器时，期望其具备强大的可迁移性。相反，测试集中的分布偏移则反映了训练好的模型遇到偏移测试样本时方法的性能表现。我们通过实验证明，现有方法在保持通用性方面存在不足，这源于其僵化的归纳偏置。受此启发，我们致力于开发具有更强适应性的归纳偏置的通用化技术。在此背景下，我们利用对比学习提供的有效框架，通过适当选择增强策略来构建负样本对，从而轻松切换并适应新的归纳偏置。我们提出了一种新颖的概率化自动负样本对生成方法AutoAugOOD，结合对比学习，构建出通用的新颖性检测方法。实验结果表明，在多个图像基准数据集的不同分布偏移下，我们的方法均表现出优越性。值得注意的是，我们的方法在适应不同新颖性检测设置（包括单类别、无标签多类别和有标签多类别设置）的视角下展现出通用性。代码地址：https://github.com/mojtaba-nafez/UNODE