Tag: ICPR 2018
-
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer, Antonio M. Lopez, Andrew D. Bagdanov Read Full Paper → In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form […]
-
Weakly Supervised Domain-Specific Color Naming Based on Attention
Lu Yu, Yongmei Cheng, Joost van de Weijer Read Full Paper → The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an […]