MM-Prompt：面向持续视觉问答的跨模态提示调优
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
AI总结：
MM-Prompt通过跨模态提示查询与恢复，解决持续视觉问答中的模态不平衡问题，提升准确性与知识保留。
摘要：
基于预训练模型的持续视觉问答（CVQA）通过利用提示调优实现持续多模态学习，已取得显著进展。然而，现有大多数方法采用跨模态提示隔离，分别构建视觉和文本提示，这加剧了模态不平衡，并导致性能随时间下降。为解决此问题，我们提出MM-Prompt，一种结合跨模态提示查询和跨模态提示恢复的新型框架。前者通过在查询形成过程中融入跨模态信号实现均衡的提示选择，而后者通过迭代跨模态交互促进联合提示重建，并由对齐损失引导以防止表征漂移。大量实验表明，MM-Prompt在准确性和知识保留方面超越先前方法，同时在持续学习过程中保持均衡的模态参与。
英文摘要：
Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cross-modal prompt isolation, constructing visual and textual prompts separately, which exacerbates modality imbalance and leads to degraded performance over time. To tackle this issue, we propose MM-Prompt, a novel framework incorporating cross-modal prompt query and cross-modal prompt recovery. The former enables balanced prompt selection by incorporating cross-modal signals during query formation, while the latter promotes joint prompt reconstruction through iterative cross-modal interactions, guided by an alignment loss to prevent representational drift. Extensive experiments show that MM-Prompt surpasses prior approaches in accuracy and knowledge retention, while maintaining balanced modality engagement throughout continual learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
