Introducing Language Guidance in Prompt-based Continual Learning


METADATA ONLY

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Continual Learning aims to learn a single model on a sequence of tasks without having access to data from previous tasks. The biggest challenge in the domain still remains catastrophic forgetting: a loss in performance on seen classes of earlier tasks. Some existing methods rely on an expensive replay buffer to store a chunk of data from previous tasks. This, while promising, becomes expensive when the number of tasks becomes large or data can not be stored for privacy reasons. As an alternative, prompt-based methods have been proposed that store the task information in a learnable prompt pool. This prompt pool instructs a frozen image encoder on how to solve each task. While the model faces a disjoint set of classes in each task in this setting, we argue that these classes can be encoded to the same embedding space of a pre-trained language encoder. In this work, we propose Language Guidance for Prompt-based Continual Learning (LGCL) as a plug-in for prompt-based methods. LGCL is model agnostic and introduces language guidance at the task level in the prompt pool and at the class level on the output feature of the vision encoder. We show with extensive experimentation that LGCL consistently improves the performance of prompt-based continual learning methods to set a new state-of-the art. LGCL achieves these performance improvements without needing any additional learnable parameters.

Permanent link

Publication status

published

Editor

Book title

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Journal / series

Volume

Pages / Article No.

11429 - 11439

Publisher

IEEE

Event

19th IEEE/CVF International Conference on Computer Vision (ICCV 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

02652 - Institut für Bildverarbeitung / Computer Vision Laboratory

Notes

Conference lecture held on October 5, 2023.

Funding

Related publications and datasets