DeepAI AI Chat
Log In Sign Up

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

by   Kai Wang, et al.

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.


page 1

page 2

page 3

page 4


Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

Continual zero-shot learning(CZSL) is a new domain to classify objects s...

Insights from the Future for Continual Learning

Continual learning aims to learn tasks sequentially, with (often severe)...

CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings

This paper presents CoLLIE: a simple, yet effective model for continual ...

Don't Stop Learning: Towards Continual Learning for the CLIP Model

The Contrastive Language-Image Pre-training (CLIP) Model is a recently p...

Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning

Continual learning is one of the key components of human learning and a ...

SPeCiaL: Self-Supervised Pretraining for Continual Learning

This paper presents SPeCiaL: a method for unsupervised pretraining of re...

Generalized Continual Zero-Shot Learning

Recently, zero-shot learning (ZSL) emerged as an exciting topic and attr...