paper-with-me

홈 › Papers

Introducing Language Guidance in Prompt-based Continual Learning

2023-08-30 · ICCV 2023 1 · Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal

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.

📄 PDF Abstract BibTeX arXiv:2308.15827

Code (1)

gulzainali98/LGCL 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

LGCL 설명 없음

Similar Papers 제목 키워드 기반

Continual Learning for Image Captioning through Improved Image-Text Alignment

2025-10-07 · Bertram Taetz, Gal Bordelius arxiv

Generating accurate and coherent image captions in a continual learning setting remains a major challenge due to catastrophic forgetting and the difficulty of aligning evolving visual concepts with language over time. In…

Continual LearningImage Captioning

Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning

2025-01-22 · Dunwei Tu, Huiyu Yi, Yuchi Wang, Baile Xu 외

Continual learning requires machine learning models to continuously acquire new knowledge in dynamic environments while avoiding the forgetting of previous knowledge. Prompt-based continual learning methods effectively a…

Continual Learning

Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation

2025-08-05 · Iing Muttakhiroh, Thomas Fevens arxiv

Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual A…

Continual LearningKnowledge Graphs

Progressive Prompts: Continual Learning for Language Models

2023-01-29 · Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa 외

We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a la…

Continual Learning

Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning

2025-11-15 · Shengqin Jiang, Tianqi Kong, Yuankai Qi, Haokui Zhang 외 arxiv

Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient adaptation to new tasks while mitigating…

Continual Learning