paper-with-me

Papers

DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning

2022-04-10 · Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi, Ruoxi Sun, Han Zhang, Chen-Yu Lee, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister

Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however, limits their practical value due to privacy and memory constraints. In this work, we present a simple yet effective framework, DualPrompt, which learns a tiny set of parameters, called prompts, to properly instruct a pre-trained model to learn tasks arriving sequentially without buffering past examples. DualPrompt presents a novel approach to attach complementary prompts to the pre-trained backbone, and then formulates the objective as learning task-invariant and task-specific "instructions". With extensive experimental validation, DualPrompt consistently sets state-of-the-art performance under the challenging class-incremental setting. In particular, DualPrompt outperforms recent advanced continual learning methods with relatively large buffer sizes. We also introduce a more challenging benchmark, Split ImageNet-R, to help generalize rehearsal-free continual learning research. Source code is available at https://github.com/google-research/l2p.

📄 PDF Abstract BibTeX arXiv:2204.04799

Code (3)

google-research/l2p 공식 구현 jax
JH-LEE-KR/dualprompt-pytorch pytorch
aimagelab/mammoth pytorch

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

2022-11-23 · CVPR 2023 1 · James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla 외

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extens…

Continual LearningNovel Concepts

A Closer Look at Rehearsal-Free Continual Learning

2022-03-31 · James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu 외

Continual learning is a setting where machine learning models learn novel concepts from continuously shifting training data, while simultaneously avoiding degradation of knowledge on previously seen classes which may dis…

Continual LearningKnowledge DistillationL2 RegularizationNovel Concepts

REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning

2024-06-07 · Sungho Jeon, Xinyue Ma, Kwang In Kim, Myeongjae Jeon

Recent rehearsal-free methods, guided by prompts, generally excel in vision-related continual learning (CL) scenarios with continuously drifting data. To be deployable on real-world devices, these methods must contain hi…

Continual Learningimage-classificationImage ClassificationPrompt Learning

INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning

2024-01-22 · Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen 외

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts tha…

class-incremental learningClass Incremental LearningContinual LearningGeneral Knowledge+1

Rehearsal-Free Modular and Compositional Continual Learning for Language Models

2024-03-31 · Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen 외

Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous t…

Continual LearningTransfer Learning