Abstract: Class-incremental semantic segmentation aims to incrementally learn new classes while maintaining the capability to segment old ones, and suffers catastrophic forgetting since the old-class ...
aCentre d'Investigations Cliniques Plurithématique 1433, Université de Lorraine, Institut National de la Santé et de la Recherche Médicale 1116, Centre Hospitalier Régional Universitaire de Nancy, ...
Abstract: Class Incremental Learning (CIL) for image classification aims to address real-world scenarios by allowing a model to learn new categories while retaining the knowledge of old categories. It ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果
反馈