TY  - CONF
AU  - Kai Wang
AU  - Luis Herranz
AU  - Anjan Dutta
AU  - Joost Van de Weijer
A2  - ECCVW
PY  - 2020//
TI  - Bookworm continual learning: beyond zero-shot learning and continual learning
BT  - Workshop TASK-CV 2020
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/WHD2020.pdf
N1  - LAMP; 600.141; 600.120
ID  - Kai Wang2020
ER  -