论文标题
发现新颖类的间距损失
Spacing Loss for Discovering Novel Categories
论文作者
论文摘要
新颖的类发现（NCD）是一种学习范式，在该范式中，机器学习模型的任务是从未标记的数据中通过使用一组段落的标记实例来从未标记的数据进行分组实例。在这项工作中，我们首先将现有的NCD方法定为单阶段和两阶段方法，这些方法是基于它们是否需要在发现新类的同时访问标签和未标记的数据。接下来，我们设计了一个简单而强大的损失函数，该功能使用多维缩放的提示在潜在空间中可分离性，我们称为间距损耗。我们提出的配方可以用作独立方法，也可以插入现有方法以增强它们。我们通过在CIFAR-10和CIFAR-100数据集的多个环境中进行彻底的实验评估来验证间距损失的功效。
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes. In this work, we first characterize existing NCD approaches into single-stage and two-stage methods based on whether they require access to labeled and unlabeled data together while discovering new classes. Next, we devise a simple yet powerful loss function that enforces separability in the latent space using cues from multi-dimensional scaling, which we refer to as Spacing Loss. Our proposed formulation can either operate as a standalone method or can be plugged into existing methods to enhance them. We validate the efficacy of Spacing Loss with thorough experimental evaluation across multiple settings on CIFAR-10 and CIFAR-100 datasets.
