论文标题
书呆子持续学习：超越零拍的学习和持续学习
Bookworm continual learning: beyond zero-shot learning and continual learning
论文作者
论文摘要
我们建议书呆子持续学习（BCL），这是一个灵活的设置，可以通过语义模型推断出看不见的类，并且可以不断更新视觉模型。因此，BCL概括了持续学习（CL）和零拍学习（ZSL）。我们还提出了双向想象力（BIMAG）框架，以解决BCL，其中生成了过去和将来的类别的特征。我们观察到，对特征发生器进行属性调节实际上会损害持续的学习能力，并提出了两个变体（联合类 - 属性调理和不对称生成）来减轻此问题。
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.
