论文标题
类锚聚类：基于距离的开放式识别的损失
Class Anchor Clustering: a Loss for Distance-based Open Set Recognition
论文作者
论文摘要
在开放式识别中，深度神经网络遇到训练过程中未知的对象类。现有的开放集分类器通过测量网络logit空间中的距离来区分已知和未知类别，假设已知类别的群集比未知类别更接近培训数据。但是，这种方法在事后将其应用于经过跨凝结损失训练的网络，这不能保证这种聚类行为。为了克服这一限制，我们介绍了类锚簇（CAC）损失。 CAC是一种基于距离的损失，明确训练已知类别，以在logit空间中的锚固依赖性中心周围形成紧密的簇。我们表明，使用CAC的培训可以在所有六个标准基准数据集上实现基于距离的开放式分类器的最先进性能，而挑战性的Tinyimagenet上的AUROC增加了15.2％，而无需牺牲分类精度。我们还表明，我们的锚定课程中心获得的开放性能比学识渊博的课程中心更高，尤其是在基于对象的数据集和大量培训课程上。
In open set recognition, deep neural networks encounter object classes that were unknown during training. Existing open set classifiers distinguish between known and unknown classes by measuring distance in a network's logit space, assuming that known classes cluster closer to the training data than unknown classes. However, this approach is applied post-hoc to networks trained with cross-entropy loss, which does not guarantee this clustering behaviour. To overcome this limitation, we introduce the Class Anchor Clustering (CAC) loss. CAC is a distance-based loss that explicitly trains known classes to form tight clusters around anchored class-dependent centres in the logit space. We show that training with CAC achieves state-of-the-art performance for distance-based open set classifiers on all six standard benchmark datasets, with a 15.2% AUROC increase on the challenging TinyImageNet, without sacrificing classification accuracy. We also show that our anchored class centres achieve higher open set performance than learnt class centres, particularly on object-based datasets and large numbers of training classes.
