# Bookworm continual learning: beyond zero-shot learning and continual learning

arXiv: https://arxiv.org/abs/2006.15176 · HTML: https://mlsanity.com/paper/2006.15176/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Continual learning in cross-modal retrieval](https://mlsanity.com/paper/2104.06806/) (2021)
- [Unseen Classes at a Later Time? No Problem](https://mlsanity.com/paper/2203.16517/) (2022)
- [On Implicit Attribute Localization for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.04704/) (2021)

## Abstract (arXiv)

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.