Spacing Loss for Discovering Novel Categories

IEEE Conference on Computer Vision and Pattern Recognition(2022)

引用 10|浏览59
暂无评分
摘要
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 singlestage 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.
更多
查看译文
关键词
spacing loss,novel class discovery,learning paradigm,machine learning model,unlabeled data,labeled instances,NCD approaches,single-stage methods,two-stage methods,powerful loss function,latent space,standalone method,novel category discovery,semantically group instances,multidimensional scaling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要