%0 Conference Proceedings
%T Bookworm continual learning: beyond zero-shot learning and continual learning
%A Kai Wang
%A Luis Herranz
%A Anjan Dutta
%A Joost Van de Weijer
%B Workshop TASK-CV 2020
%D 2020
%F Kai Wang2020
%O LAMP; 600.141; 600.120
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3466), last updated on Tue, 08 Feb 2022 12:02:27 +0100
%X We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL) and zero-shot learning (ZSL). We also propose the bidirectional imagination (BImag) framework to address BCL where features of both past and future classes are generated. We observe that conditioning the feature generator on attributes can actually harm the continual learning ability, and propose two variants (joint class-attribute conditioning and asymmetric generation) to alleviate this problem.
%U http://refbase.cvc.uab.es/files/WHD2020.pdf