The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones. However, existing top-performing methods still cause high forgetting rates, by lacking intra-domain knowledge extraction and inter-domain common prompting strategy. In this paper, we propose a simple yet effective framework, CP-Prompt, by training limited parameters to instruct a pre-trained model to learn new domains and avoid forgetting existing feature distributions. CP-Prompt captures intra-domain knowledge by compositionally inserting personalized prompts on multi-head self-attention layers and then learns the inter-domain knowledge with a common prompting strategy. CP-Prompt shows superiority compared with state-of-the-art baselines among three widely evaluated DIL tasks. The source code is available at https://github.com/dannis97500/CP_Prompt.

翻译：跨模态领域增量学习（DIL）的核心挑战在于，使学习模型能够在同一任务下持续学习来自不同特征分布的新数据，同时不遗忘旧知识。然而，现有性能最优的方法由于缺乏域内知识提取和跨域通用提示策略，仍会导致较高的遗忘率。本文提出一个简单而有效的框架——CP-Prompt，通过训练有限参数来指导预训练模型学习新领域并避免遗忘现有特征分布。CP-Prompt通过在多头自注意力层组合式插入个性化提示来捕获域内知识，随后通过通用提示策略学习跨域知识。在三个广泛评估的DIL任务中，CP-Prompt相较于最先进的基线方法均表现出优越性。源代码可在 https://github.com/dannis97500/CP_Prompt 获取。