Spacing Loss for Discovering Novel Categories
It addresses the challenge of grouping unlabeled data into novel categories using labeled data from disjoint classes, with incremental improvements to existing methods.
The paper tackles the problem of Novel Class Discovery (NCD) by introducing a Spacing Loss function that enforces separability in latent space, validated on CIFAR-10 and CIFAR-100 datasets.
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.