Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks. However, the existing pre-trained models primarily focus on effectively capturing the alignment between vision and language modalities, often ignoring the intricate nature of dialog context. In this paper, we propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval. Specifically, our approach introduces a multi-modal context prompt generator to learn context features which are subsequently distilled into prompts within the pre-trained vision-language model CLIP. Besides, we introduce domain prompt to mitigate the disc repancy from the downstream dialog data. To facilitate various types of retrieval, we also design multiple experts to learn mappings from CLIP outputs to multi-modal representation space, with each expert being responsible to one specific retrieval type. Extensive experiments show that DialCLIP achieves state-of-the-art performance on two widely recognized benchmark datasets (i.e., PhotoChat and MMDialog) by tuning a mere 0.04% of the total parameters. These results highlight the efficacy and efficiency of our proposed approach, underscoring its potential to advance the field of multi-modal dialog retrieval.

翻译：近年来，预训练视觉语言模型的显著进展极大地增强了多模态对话系统的能力。这些模型通过在下游任务上进行微调，展示了显著的性能提升。然而，现有预训练模型主要侧重于有效捕捉视觉与语言模态之间的对齐，往往忽略了对话上下文的复杂特性。本文提出一种名为DialCLIP的参数高效提示微调方法，用于多模态对话检索。具体而言，我们的方法引入多模态上下文提示生成器来学习上下文特征，并将其蒸馏到预训练视觉语言模型CLIP的提示中。此外，我们引入领域提示以缓解与下游对话数据的差异。为支持多种类型的检索，我们设计了多个专家模块，将CLIP输出映射到多模态表示空间，每个专家负责一种特定的检索类型。大量实验表明，通过仅调整0.04%的总参数，DialCLIP在两个广泛认可的基准数据集（即PhotoChat和MMDialog）上达到了最先进性能。这些结果凸显了所提方法的有效性与高效性，展示了其推动多模态对话检索领域发展的潜力。